# NC Bench > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/nc-bench%3Aoverall. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/nc-bench%3Aoverall. Author workflows covering creative writing, editing, translation, instruction following and factual reliability in Novelcrafter’s published evaluation suite. Canonical URL: https://benchize.com/benchmarks/nc-bench%3Aoverall Last updated: Wed, 21 Oct 2026 18:52:20 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Author workflows covering creative writing, editing, translation, instruction following and factual reliability in Novelcrafter’s published evaluation suite. Writing & creativity · Models tested: 144 · Score publishers: [nc bench](https://www.nc-bench.com/models) ## Model results | # | Model | Score | | | --- | --- | --- | --- | | 1 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-thinking.md)Thinking | 96.43% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 96.43 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 91.1 \| percent \| category \| Higher is better \| \| `language` \| 99.76 \| percent \| category \| Higher is better \| \| `utility` \| 98.84 \| percent \| category \| Higher is better \| \| `reasoning` \| 95.45 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.6 \| percent \| category \| Higher is better \| \| `rule_following` \| 90.06 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.63 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 5.5 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Opus 5.5 (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/0` | | | | | 2 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-medium.md)Medium | 95.88% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 95.88 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 92.05 \| percent \| category \| Higher is better \| \| `language` \| 100 \| percent \| category \| Higher is better \| \| `utility` \| 99.97 \| percent \| category \| Higher is better \| \| `reasoning` \| 97.06 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.04 \| percent \| category \| Higher is better \| \| `rule_following` \| 86.06 \| percent \| category \| Higher is better \| \| `hallucination` \| 94.9 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration GPT-6.1 Sol (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-6.1 Sol (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/2` | | | | | 3 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-medium.md)Medium | 95.72% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 95.72 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 83.1 \| percent \| category \| Higher is better \| \| `language` \| 98.16 \| percent \| category \| Higher is better \| \| `utility` \| 99.2 \| percent \| category \| Higher is better \| \| `reasoning` \| 96.72 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.84 \| percent \| category \| Higher is better \| \| `rule_following` \| 92.86 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.88 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration Gemini 3.8 Flash (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 3.8 Flash (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/3` | | | | | 4 | [Muse Wonder](https://benchize.com/models/muse-wonder-medium.md)Medium | 95.47% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 95.47 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.61 \| percent \| category \| Higher is better \| \| `language` \| 99.93 \| percent \| category \| Higher is better \| \| `utility` \| 99.83 \| percent \| category \| Higher is better \| \| `reasoning` \| 93.96 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.71 \| percent \| category \| Higher is better \| \| `rule_following` \| 86.82 \| percent \| category \| Higher is better \| \| `hallucination` \| 93.92 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration Muse Wonder (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Muse Wonder (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/5` | | | | | 5 | [GLM 5.3](https://benchize.com/models/glm-5-3-max.md)Max | 95.2% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 95.2 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 89.99 \| percent \| category \| Higher is better \| \| `language` \| 96.87 \| percent \| category \| Higher is better \| \| `utility` \| 98.44 \| percent \| category \| Higher is better \| \| `reasoning` \| 93.04 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.75 \| percent \| category \| Higher is better \| \| `rule_following` \| 89.17 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.3 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort max Model configuration Z.AI GLM 5.3 (Reasoning, Max) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Z.AI GLM 5.3 (Reasoning, Max) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/6` | | | | | 6 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-medium.md)Medium | 95.15% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 95.15 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 91.03 \| percent \| category \| Higher is better \| \| `language` \| 99.93 \| percent \| category \| Higher is better \| \| `utility` \| 97.51 \| percent \| category \| Higher is better \| \| `reasoning` \| 96.86 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.26 \| percent \| category \| Higher is better \| \| `rule_following` \| 85.88 \| percent \| category \| Higher is better \| \| `hallucination` \| 91.72 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration GPT-5.6 Sol (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.6 Sol (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/7` | | | | | 7 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6-thinking.md)Thinking | 95.06% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 95.06 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 84.55 \| percent \| category \| Higher is better \| \| `language` \| 96.12 \| percent \| category \| Higher is better \| \| `utility` \| 98.93 \| percent \| category \| Higher is better \| \| `reasoning` \| 93.19 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.86 \| percent \| category \| Higher is better \| \| `rule_following` \| 89.78 \| percent \| category \| Higher is better \| \| `hallucination` \| 99.06 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 4.6 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Opus 4.6 (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/8` | | | | | 8 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-thinking.md)Thinking | 94.9% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 94.9 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 81.02 \| percent \| category \| Higher is better \| \| `language` \| 98.22 \| percent \| category \| Higher is better \| \| `utility` \| 98.56 \| percent \| category \| Higher is better \| \| `reasoning` \| 94.48 \| percent \| category \| Higher is better \| \| `text_editing` \| 99.04 \| percent \| category \| Higher is better \| \| `rule_following` \| 90.57 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.34 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 3.6 Flash (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 3.6 Flash (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/9` | | | | | 9 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-medium.md)Medium | 94.85% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 94.85 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.99 \| percent \| category \| Higher is better \| \| `creative_writing` \| 83.06 \| percent \| category \| Higher is better \| \| `language` \| 100 \| percent \| category \| Higher is better \| \| `utility` \| 97.86 \| percent \| category \| Higher is better \| \| `reasoning` \| 95.85 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.9 \| percent \| category \| Higher is better \| \| `rule_following` \| 85.14 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.97 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration Gemini 3.7 Flash (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 3.7 Flash (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/10` | | | | | 10 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-medium.md)Medium | 94.71% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 94.71 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 87.33 \| percent \| category \| Higher is better \| \| `language` \| 100 \| percent \| category \| Higher is better \| \| `utility` \| 99.95 \| percent \| category \| Higher is better \| \| `reasoning` \| 88.79 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.76 \| percent \| category \| Higher is better \| \| `rule_following` \| 85.94 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.93 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration Muse Spark 1.2 (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Muse Spark 1.2 (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/12` | | | | | 11 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-high.md)High | 94.3% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 94.3 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 88.96 \| percent \| category \| Higher is better \| \| `language` \| 97.5 \| percent \| category \| Higher is better \| \| `utility` \| 99.43 \| percent \| category \| Higher is better \| \| `reasoning` \| 92.95 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.47 \| percent \| category \| Higher is better \| \| `rule_following` \| 81.84 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.27 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort high Model configuration DeepSeek V4.1 Flash (Reasoning, High) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label DeepSeek V4.1 Flash (Reasoning, High) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/14` | | | | | 12 | [GLM 5.3 Flash](https://benchize.com/models/glm-5-3-flash-max.md)Max | 94.28% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 94.28 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 89.46 \| percent \| category \| Higher is better \| \| `language` \| 98.73 \| percent \| category \| Higher is better \| \| `utility` \| 98.5 \| percent \| category \| Higher is better \| \| `reasoning` \| 90.49 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.59 \| percent \| category \| Higher is better \| \| `rule_following` \| 83.32 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.12 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort max Model configuration Z.AI GLM 5.3 Flash (Reasoning, Max) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Z.AI GLM 5.3 Flash (Reasoning, Max) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/15` | | | | | 13 | [DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-high.md)High | 94.12% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 94.12 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 82.08 \| percent \| category \| Higher is better \| \| `language` \| 100 \| percent \| category \| Higher is better \| \| `utility` \| 97.04 \| percent \| category \| Higher is better \| \| `reasoning` \| 91.95 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.33 \| percent \| category \| Higher is better \| \| `rule_following` \| 84.05 \| percent \| category \| Higher is better \| \| `hallucination` \| 99.51 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort high Model configuration DeepSeek V4.1 Flash 1017 (Reasoning, High) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label DeepSeek V4.1 Flash 1017 (Reasoning, High) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/18` | | | | | 13 | [Grok 4.5](https://benchize.com/models/grok-4-5-high.md)High | 94.12% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 94.12 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.99 \| percent \| category \| Higher is better \| \| `creative_writing` \| 87.43 \| percent \| category \| Higher is better \| \| `language` \| 99.82 \| percent \| category \| Higher is better \| \| `utility` \| 86.69 \| percent \| category \| Higher is better \| \| `reasoning` \| 94.45 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.73 \| percent \| category \| Higher is better \| \| `rule_following` \| 86.79 \| percent \| category \| Higher is better \| \| `hallucination` \| 99.06 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort high Model configuration Grok 4.5 (Reasoning, High) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Grok 4.5 (Reasoning, High) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/17` | | | | | 15 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview.md) | 94.08% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 94.08 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.92 \| percent \| category \| Higher is better \| \| `creative_writing` \| 85.44 \| percent \| category \| Higher is better \| \| `language` \| 94.9 \| percent \| category \| Higher is better \| \| `utility` \| 99.91 \| percent \| category \| Higher is better \| \| `reasoning` \| 88.2 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.51 \| percent \| category \| Higher is better \| \| `rule_following` \| 91.21 \| percent \| category \| Higher is better \| \| `hallucination` \| 94.53 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 3.1 Pro (Preview) thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 3.1 Pro (Preview) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/19` | | | | | 16 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-medium.md)Medium | 94.06% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 94.06 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 89.53 \| percent \| category \| Higher is better \| \| `language` \| 90 \| percent \| category \| Higher is better \| \| `utility` \| 98.62 \| percent \| category \| Higher is better \| \| `reasoning` \| 91.65 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.47 \| percent \| category \| Higher is better \| \| `rule_following` \| 85.64 \| percent \| category \| Higher is better \| \| `hallucination` \| 98.57 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration Muse Spark 1.3 (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Muse Spark 1.3 (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/20` | | | | | 17 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-high.md)High | 93.95% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 93.95 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.86 \| percent \| category \| Higher is better \| \| `language` \| 99.78 \| percent \| category \| Higher is better \| \| `utility` \| 92.68 \| percent \| category \| Higher is better \| \| `reasoning` \| 94.22 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.19 \| percent \| category \| Higher is better \| \| `rule_following` \| 80.63 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.23 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort high Model configuration GPT-6 Luna (Reasoning, High) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-6 Luna (Reasoning, High) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/21` | | | | | 18 | [GPT-5.4](https://benchize.com/models/gpt-5-4-thinking.md)Thinking | 93.85% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 93.85 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 91.17 \| percent \| category \| Higher is better \| \| `language` \| 94.9 \| percent \| category \| Higher is better \| \| `utility` \| 96.89 \| percent \| category \| Higher is better \| \| `reasoning` \| 94.89 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.42 \| percent \| category \| Higher is better \| \| `rule_following` \| 79.29 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.22 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5.4 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.4 (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/22` | | | | | 19 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-medium.md)Medium | 93.81% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 93.81 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 85.27 \| percent \| category \| Higher is better \| \| `language` \| 97.5 \| percent \| category \| Higher is better \| \| `utility` \| 98.11 \| percent \| category \| Higher is better \| \| `reasoning` \| 95.15 \| percent \| category \| Higher is better \| \| `text_editing` \| 96.47 \| percent \| category \| Higher is better \| \| `rule_following` \| 79.27 \| percent \| category \| Higher is better \| \| `hallucination` \| 98.69 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration Gemini 4 Argon (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 4 Argon (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/24` | | | | | 19 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-medium.md)Medium | 93.81% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 93.81 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 88.57 \| percent \| category \| Higher is better \| \| `language` \| 97.5 \| percent \| category \| Higher is better \| \| `utility` \| 99.4 \| percent \| category \| Higher is better \| \| `reasoning` \| 89.03 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.72 \| percent \| category \| Higher is better \| \| `rule_following` \| 80.48 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.79 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration Muse Spark 1.1 (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Muse Spark 1.1 (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/23` | | | | | 21 | [GPT-5.5](https://benchize.com/models/gpt-5-5-medium.md)Medium | 93.72% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 93.72 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.26 \| percent \| category \| Higher is better \| \| `language` \| 99.69 \| percent \| category \| Higher is better \| \| `utility` \| 96.6 \| percent \| category \| Higher is better \| \| `reasoning` \| 92.87 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.79 \| percent \| category \| Higher is better \| \| `rule_following` \| 79.4 \| percent \| category \| Higher is better \| \| `hallucination` \| 92.12 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration GPT-5.5 (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.5 (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/27` | | | | | 22 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6-thinking.md)Thinking | 93.64% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 93.64 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 83.09 \| percent \| category \| Higher is better \| \| `language` \| 97.58 \| percent \| category \| Higher is better \| \| `utility` \| 97.88 \| percent \| category \| Higher is better \| \| `reasoning` \| 89.61 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.3 \| percent \| category \| Higher is better \| \| `rule_following` \| 85.73 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.98 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Sonnet 4.6 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Sonnet 4.6 (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/28` | | | | | 23 | [GLM-5.2](https://benchize.com/models/glm-5-2-high.md)High | 93.41% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 93.41 \| percent \| reported \| Higher is better \| \| `tooling` \| 98.33 \| percent \| category \| Higher is better \| \| `creative_writing` \| 83.92 \| percent \| category \| Higher is better \| \| `language` \| 99.82 \| percent \| category \| Higher is better \| \| `utility` \| 96.31 \| percent \| category \| Higher is better \| \| `reasoning` \| 85.81 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.9 \| percent \| category \| Higher is better \| \| `rule_following` \| 85.18 \| percent \| category \| Higher is better \| \| `hallucination` \| 98.99 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort high Model configuration Z.AI GLM 5.2 (Reasoning, High) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Z.AI GLM 5.2 (Reasoning, High) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/29` | | | | | 24 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-thinking.md)Thinking | 93.35% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 93.35 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 79.87 \| percent \| category \| Higher is better \| \| `language` \| 94.41 \| percent \| category \| Higher is better \| \| `utility` \| 98.86 \| percent \| category \| Higher is better \| \| `reasoning` \| 88.22 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.78 \| percent \| category \| Higher is better \| \| `rule_following` \| 92.04 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.61 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 3.5 Flash (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 3.5 Flash (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/30` | | | | | 25 | [GLM-5 Turbo](https://benchize.com/models/glm-5-turbo.md) | 93.29% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 93.29 \| percent \| reported \| Higher is better \| \| `tooling` \| 94.3 \| percent \| category \| Higher is better \| \| `creative_writing` \| 84.66 \| percent \| category \| Higher is better \| \| `language` \| 99.9 \| percent \| category \| Higher is better \| \| `utility` \| 96.36 \| percent \| category \| Higher is better \| \| `reasoning` \| 86.87 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.17 \| percent \| category \| Higher is better \| \| `rule_following` \| 86.78 \| percent \| category \| Higher is better \| \| `hallucination` \| 99.32 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Z.AI GLM 5 Turbo thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Z.AI GLM 5 Turbo Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/31` | | | | | 26 | [Kimi K3](https://benchize.com/models/kimi-k3-high.md)High | 92.99% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.99 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 87.43 \| percent \| category \| Higher is better \| \| `language` \| 100 \| percent \| category \| Higher is better \| \| `utility` \| 96.19 \| percent \| category \| Higher is better \| \| `reasoning` \| 90.48 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.42 \| percent \| category \| Higher is better \| \| `rule_following` \| 75.43 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.97 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort high Model configuration Kimi K3 (Reasoning, High) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Kimi K3 (Reasoning, High) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/32` | | | | | 27 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-thinking.md)Thinking | 92.77% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.77 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.33 \| percent \| category \| Higher is better \| \| `language` \| 96.13 \| percent \| category \| Higher is better \| \| `utility` \| 94.61 \| percent \| category \| Higher is better \| \| `reasoning` \| 92.69 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.21 \| percent \| category \| Higher is better \| \| `rule_following` \| 74.05 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.09 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Sonnet 5.5 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Sonnet 5.5 (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/34` | | | | | 28 | [Grok 4.6](https://benchize.com/models/grok-4-6-high.md)High | 92.76% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.76 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 88.97 \| percent \| category \| Higher is better \| \| `language` \| 95.04 \| percent \| category \| Higher is better \| \| `utility` \| 83.88 \| percent \| category \| Higher is better \| \| `reasoning` \| 95.61 \| percent \| category \| Higher is better \| \| `text_editing` \| 99.17 \| percent \| category \| Higher is better \| \| `rule_following` \| 81.19 \| percent \| category \| Higher is better \| \| `hallucination` \| 98.25 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort high Model configuration Grok 4.6 (Reasoning, High) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Grok 4.6 (Reasoning, High) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/35` | | | | | 29 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-medium.md)Medium | 92.63% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.63 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.95 \| percent \| category \| Higher is better \| \| `creative_writing` \| 91.4 \| percent \| category \| Higher is better \| \| `language` \| 100 \| percent \| category \| Higher is better \| \| `utility` \| 91.07 \| percent \| category \| Higher is better \| \| `reasoning` \| 96.65 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.37 \| percent \| category \| Higher is better \| \| `rule_following` \| 69.71 \| percent \| category \| Higher is better \| \| `hallucination` \| 93.91 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration GPT-6 Sol (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-6 Sol (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/36` | | | | | 30 | [Grok 4.7](https://benchize.com/models/grok-4-7-high.md)High | 92.62% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.62 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 91.29 \| percent \| category \| Higher is better \| \| `language` \| 97.5 \| percent \| category \| Higher is better \| \| `utility` \| 91.12 \| percent \| category \| Higher is better \| \| `reasoning` \| 96.71 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.17 \| percent \| category \| Higher is better \| \| `rule_following` \| 70.68 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.48 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort high Model configuration Grok 4.7 (Reasoning, High) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Grok 4.7 (Reasoning, High) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/37` | | | | | 31 | [Kimi K2.6](https://benchize.com/models/kimi-k2-6.md) | 92.57% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.57 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.81 \| percent \| category \| Higher is better \| \| `creative_writing` \| 85.47 \| percent \| category \| Higher is better \| \| `language` \| 96.77 \| percent \| category \| Higher is better \| \| `utility` \| 97.42 \| percent \| category \| Higher is better \| \| `reasoning` \| 91.69 \| percent \| category \| Higher is better \| \| `text_editing` \| 98 \| percent \| category \| Higher is better \| \| `rule_following` \| 76.94 \| percent \| category \| Higher is better \| \| `hallucination` \| 94.43 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Kimi K2.6 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Kimi K2.6 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/38` | | | | | 32 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-thinking.md)Thinking | 92.53% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.53 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 84.73 \| percent \| category \| Higher is better \| \| `language` \| 98.77 \| percent \| category \| Higher is better \| \| `utility` \| 97.87 \| percent \| category \| Higher is better \| \| `reasoning` \| 88.52 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.58 \| percent \| category \| Higher is better \| \| `rule_following` \| 74.04 \| percent \| category \| Higher is better \| \| `hallucination` \| 98.69 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 4.7 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Opus 4.7 (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/39` | | | | | 33 | [GPT-5.5](https://benchize.com/models/gpt-5-5-low.md)Low | 92.51% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.51 \| percent \| reported \| Higher is better \| \| `tooling` \| 98.5 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.24 \| percent \| category \| Higher is better \| \| `language` \| 99.24 \| percent \| category \| Higher is better \| \| `utility` \| 96.36 \| percent \| category \| Higher is better \| \| `reasoning` \| 88.87 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.59 \| percent \| category \| Higher is better \| \| `rule_following` \| 76.9 \| percent \| category \| Higher is better \| \| `hallucination` \| 91.37 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort low Model configuration GPT-5.5 (Reasoning, Low) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.5 (Reasoning, Low) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/40` | | | | | 34 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-medium.md)Medium | 92.49% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.49 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.31 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.72 \| percent \| category \| Higher is better \| \| `language` \| 97.22 \| percent \| category \| Higher is better \| \| `utility` \| 95.58 \| percent \| category \| Higher is better \| \| `reasoning` \| 91.03 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.11 \| percent \| category \| Higher is better \| \| `rule_following` \| 72.99 \| percent \| category \| Higher is better \| \| `hallucination` \| 94.98 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration GPT-5.6 Terra (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.6 Terra (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/41` | | | | | 35 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-medium.md)Medium | 92.4% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.4 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.99 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.2 \| percent \| category \| Higher is better \| \| `language` \| 99.78 \| percent \| category \| Higher is better \| \| `utility` \| 91.17 \| percent \| category \| Higher is better \| \| `reasoning` \| 90.5 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.87 \| percent \| category \| Higher is better \| \| `rule_following` \| 73.2 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.53 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration GPT-6 Luna (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-6 Luna (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/42` | | | | | 36 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-thinking.md)Thinking | 92.33% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.33 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.53 \| percent \| category \| Higher is better \| \| `creative_writing` \| 85.25 \| percent \| category \| Higher is better \| \| `language` \| 96.38 \| percent \| category \| Higher is better \| \| `utility` \| 99.26 \| percent \| category \| Higher is better \| \| `reasoning` \| 91.76 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.78 \| percent \| category \| Higher is better \| \| `rule_following` \| 70.27 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.41 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 4.8 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Opus 4.8 (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/44` | | | | | 37 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6.md) | 92.31% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.31 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 83.59 \| percent \| category \| Higher is better \| \| `language` \| 96.13 \| percent \| category \| Higher is better \| \| `utility` \| 90.72 \| percent \| category \| Higher is better \| \| `reasoning` \| 89.75 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.35 \| percent \| category \| Higher is better \| \| `rule_following` \| 83.11 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.8 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 4.6 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Opus 4.6 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/45` | | | | | 38 | [Kimi K3](https://benchize.com/models/kimi-k3-low.md)Low | 92.07% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.07 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 86.51 \| percent \| category \| Higher is better \| \| `language` \| 99.9 \| percent \| category \| Higher is better \| \| `utility` \| 94.04 \| percent \| category \| Higher is better \| \| `reasoning` \| 89.46 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.74 \| percent \| category \| Higher is better \| \| `rule_following` \| 71.2 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.73 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort low Model configuration Kimi K3 (Reasoning, Low) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Kimi K3 (Reasoning, Low) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/47` | | | | | 39 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-low.md)Low | 92.06% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.06 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.75 \| percent \| category \| Higher is better \| \| `creative_writing` \| 88.87 \| percent \| category \| Higher is better \| \| `language` \| 99.46 \| percent \| category \| Higher is better \| \| `utility` \| 92.75 \| percent \| category \| Higher is better \| \| `reasoning` \| 88.95 \| percent \| category \| Higher is better \| \| `text_editing` \| 96.99 \| percent \| category \| Higher is better \| \| `rule_following` \| 72.36 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.34 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort low Model configuration Claude Opus 5 (Reasoning, Low) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Opus 5 (Reasoning, Low) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/48` | | | | | 40 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-low.md)Low | 91.89% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 91.89 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.48 \| percent \| category \| Higher is better \| \| `creative_writing` \| 85.86 \| percent \| category \| Higher is better \| \| `language` \| 96.31 \| percent \| category \| Higher is better \| \| `utility` \| 98 \| percent \| category \| Higher is better \| \| `reasoning` \| 88.83 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.71 \| percent \| category \| Higher is better \| \| `rule_following` \| 70.56 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.33 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort low Model configuration Claude Opus 4.8 (Reasoning, Low) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Opus 4.8 (Reasoning, Low) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/50` | | | | | 41 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 91.5% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 91.5 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 88.43 \| percent \| category \| Higher is better \| \| `language` \| 94.88 \| percent \| category \| Higher is better \| \| `utility` \| 95.96 \| percent \| category \| Higher is better \| \| `reasoning` \| 88.14 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.05 \| percent \| category \| Higher is better \| \| `rule_following` \| 72.78 \| percent \| category \| Higher is better \| \| `hallucination` \| 93.78 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Xiaomi MIMO v2.6 Pro thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Xiaomi MIMO v2.6 Pro Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/51` | | | | | 42 | [GPT-5](https://benchize.com/models/gpt-5.md) | 91.48% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 91.48 \| percent \| reported \| Higher is better \| \| `tooling` \| 98.67 \| percent \| category \| Higher is better \| \| `creative_writing` \| 86.87 \| percent \| category \| Higher is better \| \| `language` \| 91.5 \| percent \| category \| Higher is better \| \| `utility` \| 93.53 \| percent \| category \| Higher is better \| \| `reasoning` \| 89.34 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.9 \| percent \| category \| Higher is better \| \| `rule_following` \| 77.13 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.92 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/52` | | | | | 43 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-minimal.md)Minimal | 91.43% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 91.43 \| percent \| reported \| Higher is better \| \| `tooling` \| 98.33 \| percent \| category \| Higher is better \| \| `creative_writing` \| 87.3 \| percent \| category \| Higher is better \| \| `language` \| 97.5 \| percent \| category \| Higher is better \| \| `utility` \| 98.38 \| percent \| category \| Higher is better \| \| `reasoning` \| 85.18 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.6 \| percent \| category \| Higher is better \| \| `rule_following` \| 71.8 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.34 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort minimal Model configuration Muse Spark 1.1 (Reasoning, Minimal) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Muse Spark 1.1 (Reasoning, Minimal) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/53` | | | | | 44 | [GPT-5 Mini](https://benchize.com/models/gpt-5-mini.md) | 91.31% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 91.31 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.99 \| percent \| category \| Higher is better \| \| `creative_writing` \| 80.48 \| percent \| category \| Higher is better \| \| `language` \| 96.49 \| percent \| category \| Higher is better \| \| `utility` \| 98.39 \| percent \| category \| Higher is better \| \| `reasoning` \| 83.31 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.13 \| percent \| category \| Higher is better \| \| `rule_following` \| 76.44 \| percent \| category \| Higher is better \| \| `hallucination` \| 98.28 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5 Mini thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5 Mini Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/54` | | | | | 45 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-thinking.md)Thinking | 91.15% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 91.15 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.58 \| percent \| category \| Higher is better \| \| `creative_writing` \| 88.64 \| percent \| category \| Higher is better \| \| `language` \| 99.37 \| percent \| category \| Higher is better \| \| `utility` \| 93.39 \| percent \| category \| Higher is better \| \| `reasoning` \| 85.32 \| percent \| category \| Higher is better \| \| `text_editing` \| 96.91 \| percent \| category \| Higher is better \| \| `rule_following` \| 69.11 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.86 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 5 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Opus 5 (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/55` | | | | | 46 | [Grok 4.3](https://benchize.com/models/grok-4-3-thinking.md)Thinking | 90.99% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.99 \| percent \| reported \| Higher is better \| \| `tooling` \| 98.47 \| percent \| category \| Higher is better \| \| `creative_writing` \| 85.11 \| percent \| category \| Higher is better \| \| `language` \| 97.5 \| percent \| category \| Higher is better \| \| `utility` \| 92.94 \| percent \| category \| Higher is better \| \| `reasoning` \| 75.64 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.64 \| percent \| category \| Higher is better \| \| `rule_following` \| 82.8 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.86 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Grok 4.3 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Grok 4.3 (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/57` | | | | | 47 | [Grok 4.5](https://benchize.com/models/grok-4-5-low.md)Low | 90.94% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.94 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.33 \| percent \| category \| Higher is better \| \| `creative_writing` \| 87.45 \| percent \| category \| Higher is better \| \| `language` \| 94.5 \| percent \| category \| Higher is better \| \| `utility` \| 82.63 \| percent \| category \| Higher is better \| \| `reasoning` \| 89.59 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.54 \| percent \| category \| Higher is better \| \| `rule_following` \| 76.44 \| percent \| category \| Higher is better \| \| `hallucination` \| 99.01 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort low Model configuration Grok 4.5 (Reasoning, Low) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Grok 4.5 (Reasoning, Low) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/58` | | | | | 48 | [GPT-5.4](https://benchize.com/models/gpt-5-4-low.md)Low | 90.91% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.91 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.97 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.51 \| percent \| category \| Higher is better \| \| `language` \| 90.79 \| percent \| category \| Higher is better \| \| `utility` \| 95.32 \| percent \| category \| Higher is better \| \| `reasoning` \| 86.99 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.01 \| percent \| category \| Higher is better \| \| `rule_following` \| 70.02 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.71 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort low Model configuration GPT-5.4 (Reasoning, Low) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.4 (Reasoning, Low) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/59` | | | | | 49 | [Grok 4.20](https://benchize.com/models/grok-4-20-thinking.md)Thinking | 90.87% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.87 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 86.25 \| percent \| category \| Higher is better \| \| `language` \| 96.61 \| percent \| category \| Higher is better \| \| `utility` \| 92.61 \| percent \| category \| Higher is better \| \| `reasoning` \| 74.28 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.83 \| percent \| category \| Higher is better \| \| `rule_following` \| 82.04 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.3 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Grok 4.20 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Grok 4.20 (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/60` | | | | | 50 | [Kimi K2.5](https://benchize.com/models/kimi-k2-5.md) | 90.86% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.86 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 81.35 \| percent \| category \| Higher is better \| \| `language` \| 97.1 \| percent \| category \| Higher is better \| \| `utility` \| 96.63 \| percent \| category \| Higher is better \| \| `reasoning` \| 87.99 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.79 \| percent \| category \| Higher is better \| \| `rule_following` \| 72.03 \| percent \| category \| Higher is better \| \| `hallucination` \| 94.01 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Kimi K2.5 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Kimi K2.5 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/61` | | | | | 51 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol.md) | 90.76% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.76 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 91.04 \| percent \| category \| Higher is better \| \| `language` \| 94.6 \| percent \| category \| Higher is better \| \| `utility` \| 80.44 \| percent \| category \| Higher is better \| \| `reasoning` \| 91.25 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.43 \| percent \| category \| Higher is better \| \| `rule_following` \| 74.47 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.87 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5.6 Sol thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.6 Sol Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/63` | | | | | 52 | [GPT-5.1](https://benchize.com/models/gpt-5-1.md) | 90.73% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.73 \| percent \| reported \| Higher is better \| \| `tooling` \| 98.33 \| percent \| category \| Higher is better \| \| `creative_writing` \| 87.2 \| percent \| category \| Higher is better \| \| `language` \| 93.64 \| percent \| category \| Higher is better \| \| `utility` \| 95.33 \| percent \| category \| Higher is better \| \| `reasoning` \| 82.57 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.54 \| percent \| category \| Higher is better \| \| `rule_following` \| 74.05 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.22 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5.1 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.1 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/64` | | | | | 53 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6.md) | 90.66% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.66 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 83.31 \| percent \| category \| Higher is better \| \| `language` \| 100 \| percent \| category \| Higher is better \| \| `utility` \| 88.52 \| percent \| category \| Higher is better \| \| `reasoning` \| 79.62 \| percent \| category \| Higher is better \| \| `text_editing` \| 96.37 \| percent \| category \| Higher is better \| \| `rule_following` \| 82.5 \| percent \| category \| Higher is better \| \| `hallucination` \| 94.99 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Sonnet 4.6 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Sonnet 4.6 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/65` | | | | | 54 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-medium.md)Medium | 90.61% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.61 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.97 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.1 \| percent \| category \| Higher is better \| \| `language` \| 96.67 \| percent \| category \| Higher is better \| \| `utility` \| 92.18 \| percent \| category \| Higher is better \| \| `reasoning` \| 84.74 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.77 \| percent \| category \| Higher is better \| \| `rule_following` \| 64.83 \| percent \| category \| Higher is better \| \| `hallucination` \| 98.65 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration GPT-5.6 Luna (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.6 Luna (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/66` | | | | | 55 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 90.45% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.45 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.96 \| percent \| category \| Higher is better \| \| `creative_writing` \| 84.57 \| percent \| category \| Higher is better \| \| `language` \| 94.71 \| percent \| category \| Higher is better \| \| `utility` \| 93.59 \| percent \| category \| Higher is better \| \| `reasoning` \| 86.27 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.51 \| percent \| category \| Higher is better \| \| `rule_following` \| 69.18 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.83 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration MiniMax M3 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label MiniMax M3 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/67` | | | | | 56 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-thinking.md)Thinking | 90.4% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.4 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.17 \| percent \| category \| Higher is better \| \| `creative_writing` \| 81.31 \| percent \| category \| Higher is better \| \| `language` \| 99.04 \| percent \| category \| Higher is better \| \| `utility` \| 92.87 \| percent \| category \| Higher is better \| \| `reasoning` \| 87.77 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.89 \| percent \| category \| Higher is better \| \| `rule_following` \| 68.34 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.77 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Sonnet 5 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Sonnet 5 (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/68` | | | | | 57 | [DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-high.md)High | 90.21% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.21 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.79 \| percent \| category \| Higher is better \| \| `creative_writing` \| 85.72 \| percent \| category \| Higher is better \| \| `language` \| 88.93 \| percent \| category \| Higher is better \| \| `utility` \| 97.9 \| percent \| category \| Higher is better \| \| `reasoning` \| 90.05 \| percent \| category \| Higher is better \| \| `text_editing` \| 93.76 \| percent \| category \| Higher is better \| \| `rule_following` \| 76.72 \| percent \| category \| Higher is better \| \| `hallucination` \| 88.77 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort high Model configuration DeepSeek V4 Pro 0813 (Reasoning, High) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label DeepSeek V4 Pro 0813 (Reasoning, High) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/70` | | | | | 58 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-low.md)Low | 90.16% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.16 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.52 \| percent \| category \| Higher is better \| \| `creative_writing` \| 81.43 \| percent \| category \| Higher is better \| \| `language` \| 98.06 \| percent \| category \| Higher is better \| \| `utility` \| 93.53 \| percent \| category \| Higher is better \| \| `reasoning` \| 87.78 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.93 \| percent \| category \| Higher is better \| \| `rule_following` \| 66.62 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.44 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort low Model configuration Claude Sonnet 5 (Reasoning, Low) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Sonnet 5 (Reasoning, Low) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/71` | | | | | 59 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol.md) | 90.05% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.05 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.95 \| percent \| category \| Higher is better \| \| `creative_writing` \| 91.22 \| percent \| category \| Higher is better \| \| `language` \| 100 \| percent \| category \| Higher is better \| \| `utility` \| 81.18 \| percent \| category \| Higher is better \| \| `reasoning` \| 92.95 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.56 \| percent \| category \| Higher is better \| \| `rule_following` \| 67.23 \| percent \| category \| Higher is better \| \| `hallucination` \| 89.32 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-6 Sol thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-6 Sol Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/72` | | | | | 60 | [Claude Opus 5](https://benchize.com/models/claude-opus-5.md) | 89.97% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 89.97 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.77 \| percent \| category \| Higher is better \| \| `creative_writing` \| 88.13 \| percent \| category \| Higher is better \| \| `language` \| 99.73 \| percent \| category \| Higher is better \| \| `utility` \| 90.5 \| percent \| category \| Higher is better \| \| `reasoning` \| 85.64 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.06 \| percent \| category \| Higher is better \| \| `rule_following` \| 64.01 \| percent \| category \| Higher is better \| \| `hallucination` \| 93.91 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 5 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Opus 5 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/74` | | | | | 61 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7.md) | 89.9% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 89.9 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.48 \| percent \| category \| Higher is better \| \| `creative_writing` \| 84.74 \| percent \| category \| Higher is better \| \| `language` \| 92.32 \| percent \| category \| Higher is better \| \| `utility` \| 95.77 \| percent \| category \| Higher is better \| \| `reasoning` \| 88.29 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.55 \| percent \| category \| Higher is better \| \| `rule_following` \| 68.08 \| percent \| category \| Higher is better \| \| `hallucination` \| 92.95 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 4.7 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Opus 4.7 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/76` | | | | | 62 | [GPT-5.4 Mini](https://benchize.com/models/gpt-5-4-mini-thinking.md)Thinking | 89.82% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 89.82 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 88.66 \| percent \| category \| Higher is better \| \| `language` \| 98.12 \| percent \| category \| Higher is better \| \| `utility` \| 94.44 \| percent \| category \| Higher is better \| \| `reasoning` \| 86.1 \| percent \| category \| Higher is better \| \| `text_editing` \| 95.78 \| percent \| category \| Higher is better \| \| `rule_following` \| 57.38 \| percent \| category \| Higher is better \| \| `hallucination` \| 98.11 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5.4 Mini (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.4 Mini (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/77` | | | | | 63 | [Gemma 4 31B](https://benchize.com/models/gemma-4-31b-it-thinking.md)Thinking | 89.64% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 89.64 \| percent \| reported \| Higher is better \| \| `tooling` \| 98.5 \| percent \| category \| Higher is better \| \| `creative_writing` \| 78.13 \| percent \| category \| Higher is better \| \| `language` \| 83.82 \| percent \| category \| Higher is better \| \| `utility` \| 96.32 \| percent \| category \| Higher is better \| \| `reasoning` \| 80.14 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.83 \| percent \| category \| Higher is better \| \| `rule_following` \| 85 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.37 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemma 4 31B (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemma 4 31B (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/79` | | | | | 64 | [Claude Opus 4.5](https://benchize.com/models/claude-opus-4-5.md) | 89.6% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 89.6 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 81.71 \| percent \| category \| Higher is better \| \| `language` \| 99.66 \| percent \| category \| Higher is better \| \| `utility` \| 89.84 \| percent \| category \| Higher is better \| \| `reasoning` \| 84.25 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.69 \| percent \| category \| Higher is better \| \| `rule_following` \| 72.61 \| percent \| category \| Higher is better \| \| `hallucination` \| 91.03 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 4.5 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Opus 4.5 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/80` | | | | | 64 | [GLM-5](https://benchize.com/models/glm-5.md) | 89.6% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 89.6 \| percent \| reported \| Higher is better \| \| `tooling` \| 98.5 \| percent \| category \| Higher is better \| \| `creative_writing` \| 83.63 \| percent \| category \| Higher is better \| \| `language` \| 92.06 \| percent \| category \| Higher is better \| \| `utility` \| 94.11 \| percent \| category \| Higher is better \| \| `reasoning` \| 84.09 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.59 \| percent \| category \| Higher is better \| \| `rule_following` \| 67.78 \| percent \| category \| Higher is better \| \| `hallucination` \| 98.04 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Z.AI GLM 5 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Z.AI GLM 5 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/81` | | | | | 66 | [GPT-5.2](https://benchize.com/models/gpt-5-2.md) | 89.45% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 89.45 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 80.36 \| percent \| category \| Higher is better \| \| `language` \| 91.19 \| percent \| category \| Higher is better \| \| `utility` \| 96.22 \| percent \| category \| Higher is better \| \| `reasoning` \| 85.61 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.54 \| percent \| category \| Higher is better \| \| `rule_following` \| 67.1 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.55 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5.2 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.2 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/83` | | | | | 67 | [GPT-5.5](https://benchize.com/models/gpt-5-5.md) | 89.37% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 89.37 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.39 \| percent \| category \| Higher is better \| \| `language` \| 94.15 \| percent \| category \| Higher is better \| \| `utility` \| 81.88 \| percent \| category \| Higher is better \| \| `reasoning` \| 87.68 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.2 \| percent \| category \| Higher is better \| \| `rule_following` \| 72.34 \| percent \| category \| Higher is better \| \| `hallucination` \| 90.28 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5.5 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.5 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/85` | | | | | 67 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-adaptive.md)Adaptive | 89.37% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 89.37 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 88.73 \| percent \| category \| Higher is better \| \| `language` \| 99.77 \| percent \| category \| Higher is better \| \| `utility` \| 91.83 \| percent \| category \| Higher is better \| \| `reasoning` \| 85.05 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.15 \| percent \| category \| Higher is better \| \| `rule_following` \| 56.33 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.12 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Haiku 5.5 (Adaptive) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Haiku 5.5 (Adaptive) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/84` | | | | | 69 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro-thinking.md)Thinking | 89.28% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 89.28 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.4 \| percent \| category \| Higher is better \| \| `creative_writing` \| 82.99 \| percent \| category \| Higher is better \| \| `language` \| 88.51 \| percent \| category \| Higher is better \| \| `utility` \| 93.24 \| percent \| category \| Higher is better \| \| `reasoning` \| 83.52 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.56 \| percent \| category \| Higher is better \| \| `rule_following` \| 72.74 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.25 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration DeepSeek V4 Pro (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label DeepSeek V4 Pro (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/87` | | | | | 70 | [Muse Glimmer 30B](https://benchize.com/models/muse-glimmer-30b-medium.md)Medium | 88.81% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 88.81 \| percent \| reported \| Higher is better \| \| `tooling` \| 93.33 \| percent \| category \| Higher is better \| \| `creative_writing` \| 87.42 \| percent \| category \| Higher is better \| \| `language` \| 99.91 \| percent \| category \| Higher is better \| \| `utility` \| 96.62 \| percent \| category \| Higher is better \| \| `reasoning` \| 76.61 \| percent \| category \| Higher is better \| \| `text_editing` \| 96.91 \| percent \| category \| Higher is better \| \| `rule_following` \| 63.51 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.19 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration Muse Glimmer 30B (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Muse Glimmer 30B (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/89` | | | | | 71 | [Aion-3.0](https://benchize.com/models/aion-3-0.md) | 88.78% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 88.78 \| percent \| reported \| Higher is better \| \| `tooling` \| 96.54 \| percent \| category \| Higher is better \| \| `creative_writing` \| 84.64 \| percent \| category \| Higher is better \| \| `language` \| 86.85 \| percent \| category \| Higher is better \| \| `utility` \| 93.57 \| percent \| category \| Higher is better \| \| `reasoning` \| 86.56 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.73 \| percent \| category \| Higher is better \| \| `rule_following` \| 68.8 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.57 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Aion 3.0 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Aion 3.0 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/90` | | | | | 71 | [o4 Mini High](https://benchize.com/models/o4-mini-high.md) | 88.78% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 88.78 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 82.72 \| percent \| category \| Higher is better \| \| `language` \| 79.76 \| percent \| category \| Higher is better \| \| `utility` \| 98.67 \| percent \| category \| Higher is better \| \| `reasoning` \| 82.51 \| percent \| category \| Higher is better \| \| `text_editing` \| 94.36 \| percent \| category \| Higher is better \| \| `rule_following` \| 72.7 \| percent \| category \| Higher is better \| \| `hallucination` \| 99.53 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration o4 Mini High thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label o4 Mini High Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/91` | | | | | 73 | [GLM 5.3 Flash](https://benchize.com/models/glm-5-3-flash-low.md)Low | 88.76% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 88.76 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 86.13 \| percent \| category \| Higher is better \| \| `language` \| 97.14 \| percent \| category \| Higher is better \| \| `utility` \| 90.95 \| percent \| category \| Higher is better \| \| `reasoning` \| 78.82 \| percent \| category \| Higher is better \| \| `text_editing` \| 92.97 \| percent \| category \| Higher is better \| \| `rule_following` \| 64.71 \| percent \| category \| Higher is better \| \| `hallucination` \| 99.36 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort low Model configuration Z.AI GLM 5.3 Flash (Reasoning, Low) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Z.AI GLM 5.3 Flash (Reasoning, Low) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/92` | | | | | 74 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 88.44% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 88.44 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 81.03 \| percent \| category \| Higher is better \| \| `language` \| 92.57 \| percent \| category \| Higher is better \| \| `utility` \| 92.18 \| percent \| category \| Higher is better \| \| `reasoning` \| 89.21 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.58 \| percent \| category \| Higher is better \| \| `rule_following` \| 60.89 \| percent \| category \| Higher is better \| \| `hallucination` \| 93.05 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 2.5 Pro thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 2.5 Pro Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/94` | | | | | 75 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra.md) | 88.23% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 88.23 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.33 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.92 \| percent \| category \| Higher is better \| \| `language` \| 91.87 \| percent \| category \| Higher is better \| \| `utility` \| 77.09 \| percent \| category \| Higher is better \| \| `reasoning` \| 84.98 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.21 \| percent \| category \| Higher is better \| \| `rule_following` \| 72.82 \| percent \| category \| Higher is better \| \| `hallucination` \| 90.63 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5.6 Terra thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.6 Terra Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/96` | | | | | 76 | [DeepSeek V4 Flash](https://benchize.com/models/deepseek-v4-flash-thinking.md)Thinking | 88.06% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 88.06 \| percent \| reported \| Higher is better \| \| `tooling` \| 96.17 \| percent \| category \| Higher is better \| \| `creative_writing` \| 83.03 \| percent \| category \| Higher is better \| \| `language` \| 94.76 \| percent \| category \| Higher is better \| \| `utility` \| 87.53 \| percent \| category \| Higher is better \| \| `reasoning` \| 85.45 \| percent \| category \| Higher is better \| \| `text_editing` \| 96.15 \| percent \| category \| Higher is better \| \| `rule_following` \| 64.5 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.92 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration DeepSeek V4 Flash (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label DeepSeek V4 Flash (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/97` | | | | | 77 | [DeepSeek V4 Flash 0731](https://benchize.com/models/deepseek-v4-flash-0731-high.md)High | 87.97% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 87.97 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.13 \| percent \| category \| Higher is better \| \| `creative_writing` \| 84.03 \| percent \| category \| Higher is better \| \| `language` \| 82.6 \| percent \| category \| Higher is better \| \| `utility` \| 94.25 \| percent \| category \| Higher is better \| \| `reasoning` \| 94.38 \| percent \| category \| Higher is better \| \| `text_editing` \| 94.92 \| percent \| category \| Higher is better \| \| `rule_following` \| 60.15 \| percent \| category \| Higher is better \| \| `hallucination` \| 94.32 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort high Model configuration DeepSeek V4 Flash 0731 (Reasoning, High) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label DeepSeek V4 Flash 0731 (Reasoning, High) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/98` | | | | | 78 | [Claude Sonnet 4](https://benchize.com/models/claude-sonnet-4.md) | 87.64% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 87.64 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 79.21 \| percent \| category \| Higher is better \| \| `language` \| 91.31 \| percent \| category \| Higher is better \| \| `utility` \| 84.02 \| percent \| category \| Higher is better \| \| `reasoning` \| 75.86 \| percent \| category \| Higher is better \| \| `text_editing` \| 99.13 \| percent \| category \| Higher is better \| \| `rule_following` \| 81.52 \| percent \| category \| Higher is better \| \| `hallucination` \| 90.04 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Sonnet 4 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Sonnet 4 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/102` | | | | | 78 | [GLM-4.6](https://benchize.com/models/glm-4-6.md) | 87.64% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 87.64 \| percent \| reported \| Higher is better \| \| `tooling` \| 97.99 \| percent \| category \| Higher is better \| \| `creative_writing` \| 78.86 \| percent \| category \| Higher is better \| \| `language` \| 96.6 \| percent \| category \| Higher is better \| \| `utility` \| 88.58 \| percent \| category \| Higher is better \| \| `reasoning` \| 81.01 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.78 \| percent \| category \| Higher is better \| \| `rule_following` \| 65.85 \| percent \| category \| Higher is better \| \| `hallucination` \| 94.42 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Z.AI GLM 4.6 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Z.AI GLM 4.6 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/101` | | | | | 80 | [Claude Sonnet 4.5](https://benchize.com/models/claude-sonnet-4-5.md) | 87.54% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 87.54 \| percent \| reported \| Higher is better \| \| `tooling` \| 97.75 \| percent \| category \| Higher is better \| \| `creative_writing` \| 84.19 \| percent \| category \| Higher is better \| \| `language` \| 92.39 \| percent \| category \| Higher is better \| \| `utility` \| 83.78 \| percent \| category \| Higher is better \| \| `reasoning` \| 78.61 \| percent \| category \| Higher is better \| \| `text_editing` \| 99.02 \| percent \| category \| Higher is better \| \| `rule_following` \| 76.8 \| percent \| category \| Higher is better \| \| `hallucination` \| 87.78 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Sonnet 4.5 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Sonnet 4.5 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/103` | | | | | 81 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5.md) | 87.34% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 87.34 \| percent \| reported \| Higher is better \| \| `tooling` \| 95.99 \| percent \| category \| Higher is better \| \| `creative_writing` \| 82.58 \| percent \| category \| Higher is better \| \| `language` \| 95.5 \| percent \| category \| Higher is better \| \| `utility` \| 88.57 \| percent \| category \| Higher is better \| \| `reasoning` \| 75.35 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.65 \| percent \| category \| Higher is better \| \| `rule_following` \| 74.36 \| percent \| category \| Higher is better \| \| `hallucination` \| 88.74 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Sonnet 5 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Sonnet 5 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/105` | | | | | 82 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 87.31% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 87.31 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.77 \| percent \| category \| Higher is better \| \| `creative_writing` \| 84.08 \| percent \| category \| Higher is better \| \| `language` \| 88.24 \| percent \| category \| Higher is better \| \| `utility` \| 88.05 \| percent \| category \| Higher is better \| \| `reasoning` \| 90.43 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.6 \| percent \| category \| Higher is better \| \| `rule_following` \| 52.54 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.74 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Xiaomi MIMO v2.6 Flash thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Xiaomi MIMO v2.6 Flash Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/106` | | | | | 83 | [Claude Opus 4](https://benchize.com/models/claude-opus-4.md) | 87.22% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 87.22 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 83.79 \| percent \| category \| Higher is better \| \| `language` \| 93.01 \| percent \| category \| Higher is better \| \| `utility` \| 88.81 \| percent \| category \| Higher is better \| \| `reasoning` \| 76.72 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.25 \| percent \| category \| Higher is better \| \| `rule_following` \| 70.37 \| percent \| category \| Higher is better \| \| `hallucination` \| 87.84 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 4 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Opus 4 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/107` | | | | | 84 | [GPT-4.1](https://benchize.com/models/gpt-4-1.md) | 86.82% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 86.82 \| percent \| reported \| Higher is better \| \| `tooling` \| 97.71 \| percent \| category \| Higher is better \| \| `creative_writing` \| 81.24 \| percent \| category \| Higher is better \| \| `language` \| 93.91 \| percent \| category \| Higher is better \| \| `utility` \| 90.57 \| percent \| category \| Higher is better \| \| `reasoning` \| 74.4 \| percent \| category \| Higher is better \| \| `text_editing` \| 94.4 \| percent \| category \| Higher is better \| \| `rule_following` \| 66.78 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.6 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4.1 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-4.1 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/109` | | | | | 85 | [MiniMax M2.5](https://benchize.com/models/minimax-m2-5.md) | 86.71% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 86.71 \| percent \| reported \| Higher is better \| \| `tooling` \| 98.27 \| percent \| category \| Higher is better \| \| `creative_writing` \| 81.21 \| percent \| category \| Higher is better \| \| `language` \| 96.05 \| percent \| category \| Higher is better \| \| `utility` \| 90.42 \| percent \| category \| Higher is better \| \| `reasoning` \| 74.33 \| percent \| category \| Higher is better \| \| `text_editing` \| 96.02 \| percent \| category \| Higher is better \| \| `rule_following` \| 62.69 \| percent \| category \| Higher is better \| \| `hallucination` \| 94.72 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration MiniMax M2.5 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label MiniMax M2.5 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/110` | | | | | 86 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-minimal.md)Minimal | 86.68% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 86.68 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.33 \| percent \| category \| Higher is better \| \| `creative_writing` \| 79.25 \| percent \| category \| Higher is better \| \| `language` \| 97.5 \| percent \| category \| Higher is better \| \| `utility` \| 84.77 \| percent \| category \| Higher is better \| \| `reasoning` \| 83.4 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.36 \| percent \| category \| Higher is better \| \| `rule_following` \| 54.33 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.53 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort minimal Model configuration Gemini 3.6 Flash (Reasoning, Minimal) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 3.6 Flash (Reasoning, Minimal) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/111` | | | | | 87 | [Aion 2.0](https://benchize.com/models/aion-2-0.md) | 86.66% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 86.66 \| percent \| reported \| Higher is better \| \| `tooling` \| 95.1 \| percent \| category \| Higher is better \| \| `creative_writing` \| 80.24 \| percent \| category \| Higher is better \| \| `language` \| 96.17 \| percent \| category \| Higher is better \| \| `utility` \| 90.91 \| percent \| category \| Higher is better \| \| `reasoning` \| 78.64 \| percent \| category \| Higher is better \| \| `text_editing` \| 95.34 \| percent \| category \| Higher is better \| \| `rule_following` \| 63.77 \| percent \| category \| Higher is better \| \| `hallucination` \| 93.1 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Aion 2.0 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Aion 2.0 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/112` | | | | | 88 | [O4 Mini](https://benchize.com/models/o4-mini.md) | 86.56% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 86.56 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 82.04 \| percent \| category \| Higher is better \| \| `language` \| 80 \| percent \| category \| Higher is better \| \| `utility` \| 96.31 \| percent \| category \| Higher is better \| \| `reasoning` \| 80.39 \| percent \| category \| Higher is better \| \| `text_editing` \| 90.61 \| percent \| category \| Higher is better \| \| `rule_following` \| 64.61 \| percent \| category \| Higher is better \| \| `hallucination` \| 98.54 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration o4 Mini thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label o4 Mini Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/113` | | | | | 89 | [MiniMax M2.7](https://benchize.com/models/minimax-m2-7.md) | 86.23% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 86.23 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.32 \| percent \| category \| Higher is better \| \| `creative_writing` \| 81.7 \| percent \| category \| Higher is better \| \| `language` \| 84.8 \| percent \| category \| Higher is better \| \| `utility` \| 95.5 \| percent \| category \| Higher is better \| \| `reasoning` \| 72.76 \| percent \| category \| Higher is better \| \| `text_editing` \| 92.14 \| percent \| category \| Higher is better \| \| `rule_following` \| 68.9 \| percent \| category \| Higher is better \| \| `hallucination` \| 94.69 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration MiniMax M2.7 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label MiniMax M2.7 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/114` | | | | | 90 | [MiMo-V2.5-Pro](https://benchize.com/models/mimo-v2-5-pro.md) | 86.05% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 86.05 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 81.08 \| percent \| category \| Higher is better \| \| `language` \| 87.69 \| percent \| category \| Higher is better \| \| `utility` \| 82.62 \| percent \| category \| Higher is better \| \| `reasoning` \| 79.73 \| percent \| category \| Higher is better \| \| `text_editing` \| 95.96 \| percent \| category \| Higher is better \| \| `rule_following` \| 64.29 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.02 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Xiaomi MIMO v2.5 Pro thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Xiaomi MIMO v2.5 Pro Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/116` | | | | | 91 | [Gemini 3.1 Flash Lite](https://benchize.com/models/gemini-3-1-flash-lite-thinking.md)Thinking | 85.91% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 85.91 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.81 \| percent \| category \| Higher is better \| \| `creative_writing` \| 76.31 \| percent \| category \| Higher is better \| \| `language` \| 96.7 \| percent \| category \| Higher is better \| \| `utility` \| 92.32 \| percent \| category \| Higher is better \| \| `reasoning` \| 75.32 \| percent \| category \| Higher is better \| \| `text_editing` \| 96.9 \| percent \| category \| Higher is better \| \| `rule_following` \| 62.26 \| percent \| category \| Higher is better \| \| `hallucination` \| 87.63 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 3.1 Flash Lite (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 3.1 Flash Lite (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/117` | | | | | 92 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-minimal.md)Minimal | 85.88% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 85.88 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 78.55 \| percent \| category \| Higher is better \| \| `language` \| 97.5 \| percent \| category \| Higher is better \| \| `utility` \| 83.9 \| percent \| category \| Higher is better \| \| `reasoning` \| 78.93 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.26 \| percent \| category \| Higher is better \| \| `rule_following` \| 60.38 \| percent \| category \| Higher is better \| \| `hallucination` \| 89.55 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort minimal Model configuration Gemini 3.5 Flash (Reasoning, Minimal) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 3.5 Flash (Reasoning, Minimal) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/118` | | | | | 93 | [Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview.md) | 85.47% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 85.47 \| percent \| reported \| Higher is better \| \| `tooling` \| 98.04 \| percent \| category \| Higher is better \| \| `creative_writing` \| 75.04 \| percent \| category \| Higher is better \| \| `language` \| 95 \| percent \| category \| Higher is better \| \| `utility` \| 86.39 \| percent \| category \| Higher is better \| \| `reasoning` \| 80.99 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.54 \| percent \| category \| Higher is better \| \| `rule_following` \| 65.14 \| percent \| category \| Higher is better \| \| `hallucination` \| 85.61 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 3 Flash (Preview) thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 3 Flash (Preview) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/121` | | | | | 94 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview.md) | 85.41% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 85.41 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.98 \| percent \| category \| Higher is better \| \| `creative_writing` \| 75.78 \| percent \| category \| Higher is better \| \| `language` \| 94.98 \| percent \| category \| Higher is better \| \| `utility` \| 94 \| percent \| category \| Higher is better \| \| `reasoning` \| 75.75 \| percent \| category \| Higher is better \| \| `text_editing` \| 96.46 \| percent \| category \| Higher is better \| \| `rule_following` \| 59.04 \| percent \| category \| Higher is better \| \| `hallucination` \| 87.29 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 3.1 Flash Lite (Preview) thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 3.1 Flash Lite (Preview) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/122` | | | | | 95 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5-thinking.md)Thinking | 85.32% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 85.32 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 81.67 \| percent \| category \| Higher is better \| \| `language` \| 93.44 \| percent \| category \| Higher is better \| \| `utility` \| 74.19 \| percent \| category \| Higher is better \| \| `reasoning` \| 74.65 \| percent \| category \| Higher is better \| \| `text_editing` \| 95.83 \| percent \| category \| Higher is better \| \| `rule_following` \| 73.42 \| percent \| category \| Higher is better \| \| `hallucination` \| 89.37 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Mistral Medium 3.5 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Mistral Medium 3.5 (Reasoning) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/123` | | | | | 96 | [Gemma 4 31B](https://benchize.com/models/gemma-4-31b-it.md) | 85.23% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 85.23 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 75.59 \| percent \| category \| Higher is better \| \| `language` \| 75 \| percent \| category \| Higher is better \| \| `utility` \| 86.69 \| percent \| category \| Higher is better \| \| `reasoning` \| 78.18 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.56 \| percent \| category \| Higher is better \| \| `rule_following` \| 72.72 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.09 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemma 4 31B thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemma 4 31B Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/124` | | | | | 97 | [Gemini 3.1 Flash Lite](https://benchize.com/models/gemini-3-1-flash-lite.md) | 85.09% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 85.09 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.97 \| percent \| category \| Higher is better \| \| `creative_writing` \| 76.01 \| percent \| category \| Higher is better \| \| `language` \| 90.9 \| percent \| category \| Higher is better \| \| `utility` \| 92.77 \| percent \| category \| Higher is better \| \| `reasoning` \| 74.62 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.35 \| percent \| category \| Higher is better \| \| `rule_following` \| 61.21 \| percent \| category \| Higher is better \| \| `hallucination` \| 87.86 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 3.1 Flash Lite thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 3.1 Flash Lite Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/125` | | | | | 98 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna.md) | 85.06% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 85.06 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.9 \| percent \| category \| Higher is better \| \| `creative_writing` \| 89.69 \| percent \| category \| Higher is better \| \| `language` \| 99.33 \| percent \| category \| Higher is better \| \| `utility` \| 75 \| percent \| category \| Higher is better \| \| `reasoning` \| 72.88 \| percent \| category \| Higher is better \| \| `text_editing` \| 95.6 \| percent \| category \| Higher is better \| \| `rule_following` \| 54.7 \| percent \| category \| Higher is better \| \| `hallucination` \| 93.37 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5.6 Luna thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.6 Luna Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/126` | | | | | 99 | [GLM-4.5](https://benchize.com/models/glm-4-5.md) | 84.95% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 84.95 \| percent \| reported \| Higher is better \| \| `tooling` \| 98.58 \| percent \| category \| Higher is better \| \| `creative_writing` \| 76.56 \| percent \| category \| Higher is better \| \| `language` \| 97.33 \| percent \| category \| Higher is better \| \| `utility` \| 79.19 \| percent \| category \| Higher is better \| \| `reasoning` \| 77 \| percent \| category \| Higher is better \| \| `text_editing` \| 95.32 \| percent \| category \| Higher is better \| \| `rule_following` \| 63.79 \| percent \| category \| Higher is better \| \| `hallucination` \| 91.83 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Z.AI GLM 4.5 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Z.AI GLM 4.5 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/127` | | | | | 100 | [gpt-oss-120b](https://benchize.com/models/gpt-oss-120b.md) | 84.81% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 84.81 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 67.85 \| percent \| category \| Higher is better \| \| `language` \| 97.18 \| percent \| category \| Higher is better \| \| `utility` \| 92.03 \| percent \| category \| Higher is better \| \| `reasoning` \| 77 \| percent \| category \| Higher is better \| \| `text_editing` \| 91.73 \| percent \| category \| Higher is better \| \| `rule_following` \| 55.03 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.63 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-OSS 120B thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-OSS 120B Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/129` | | | | [Next page](https://benchize.com/benchmarks/nc-bench%3Aoverall.md?cursor=%7B%22score%22%3A84.81%2C%22id%22%3A%22a2f955a9bc148f7fc8e5ea91181af6898ac3dbd71e11c7e972658bfba922712a%22%7D) --- Cite as: NC Bench — Benchize, https://benchize.com/benchmarks/nc-bench%3Aoverall (retrieved 2026-10-21)