# LiveBench > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/livebench%3Atasks. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/livebench%3Atasks. Regularly refreshed reasoning, mathematics, coding, language, instruction-following and data-analysis tasks with objectively graded answers. The original release publishes per-category scores and a global average, and its release date remains part of every reported configuration. Canonical URL: https://benchize.com/benchmarks/livebench%3Atasks 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. Regularly refreshed reasoning, mathematics, coding, language, instruction-following and data-analysis tasks with objectively graded answers. The original release publishes per-category scores and a global average, and its release date remains part of every reported configuration. Composite indexes · Models tested: 10 · Score publishers: [LiveBench](https://livebench.ai/) ## Model results | # | Model | Score | | | --- | --- | --- | --- | | 1 | [GLM-5.2](https://benchize.com/models/glm-5-2.md) | 98% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `AMPS_Hard` \| 98 \| percent \| reported \| Higher is better \| \| `code_completion` \| 80.435 \| percent \| reported \| Higher is better \| \| `code_generation` \| 78.873 \| percent \| reported \| Higher is better \| \| `connections` \| 94 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 79.276 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 76 \| percent \| reported \| Higher is better \| \| `javascript` \| 59.091 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 80 \| percent \| reported \| Higher is better \| \| `math_comp` \| 96.078 \| percent \| reported \| Higher is better \| \| `olympiad` \| 89.047 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 62.25 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 60.725 \| percent \| reported \| Higher is better \| \| `python` \| 50 \| percent \| reported \| Higher is better \| \| `simplify` \| 55.667 \| percent \| reported \| Higher is better \| \| `spatial` \| 94 \| percent \| reported \| Higher is better \| \| `story_generation` \| 62.883 \| percent \| reported \| Higher is better \| \| `summarize` \| 68.367 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 45.865 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 96.078 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 75 \| percent \| reported \| Higher is better \| \| `typescript` \| 46.667 \| percent \| reported \| Higher is better \| \| `typos` \| 74 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 65.5 \| percent \| reported \| Higher is better \| ### Configuration Model configuration glm-5.2 sourceRelease 2026_06_25 ### Source [Original source](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) Source LiveBench Original model label glm-5.2 Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/11` | | | | | 1 | [DeepSeek V4 Flash](https://benchize.com/models/deepseek-v4-flash.md) | 98% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `AMPS_Hard` \| 98 \| percent \| reported \| Higher is better \| \| `code_completion` \| 65.217 \| percent \| reported \| Higher is better \| \| `code_generation` \| 73.239 \| percent \| reported \| Higher is better \| \| `connections` \| 89.5 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 59.915 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 37 \| percent \| reported \| Higher is better \| \| `javascript` \| 54.545 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 64 \| percent \| reported \| Higher is better \| \| `math_comp` \| 97.059 \| percent \| reported \| Higher is better \| \| `olympiad` \| 86.531 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 62.383 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 46.872 \| percent \| reported \| Higher is better \| \| `python` \| 35 \| percent \| reported \| Higher is better \| \| `simplify` \| 54.05 \| percent \| reported \| Higher is better \| \| `spatial` \| 96 \| percent \| reported \| Higher is better \| \| `story_generation` \| 67.267 \| percent \| reported \| Higher is better \| \| `summarize` \| 68.85 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 46.115 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 98.039 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 73.077 \| percent \| reported \| Higher is better \| \| `typescript` \| 23.333 \| percent \| reported \| Higher is better \| \| `typos` \| 74 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 49.25 \| percent \| reported \| Higher is better \| ### Configuration Model configuration deepseek-v4-flash sourceRelease 2026_06_25 ### Source [Original source](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) Source LiveBench Original model label deepseek-v4-flash Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/7` | | | | | 1 | [GPT-5.5](https://benchize.com/models/gpt-5-5.md) | 98% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `AMPS_Hard` \| 98 \| percent \| reported \| Higher is better \| \| `code_completion` \| 82.609 \| percent \| reported \| Higher is better \| \| `code_generation` \| 74.648 \| percent \| reported \| Higher is better \| \| `connections` \| 100 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 78.23 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 85 \| percent \| reported \| Higher is better \| \| `javascript` \| 50 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 76 \| percent \| reported \| Higher is better \| \| `math_comp` \| 96.078 \| percent \| reported \| Higher is better \| \| `olympiad` \| 0 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 63.6 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 70.711 \| percent \| reported \| Higher is better \| \| `python` \| 50 \| percent \| reported \| Higher is better \| \| `simplify` \| 58.733 \| percent \| reported \| Higher is better \| \| `spatial` \| 98 \| percent \| reported \| Higher is better \| \| `story_generation` \| 67.2 \| percent \| reported \| Higher is better \| \| `summarize` \| 73.417 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 52.731 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 100 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 78.846 \| percent \| reported \| Higher is better \| \| `typescript` \| 23.333 \| percent \| reported \| Higher is better \| \| `typos` \| 86 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 96.25 \| percent \| reported \| Higher is better \| ### Configuration Model configuration gpt-5.5 sourceRelease 2026_06_25 ### Source [Original source](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) Source LiveBench Original model label gpt-5.5 Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/17` | | | | | 1 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro.md) | 98% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `AMPS_Hard` \| 98 \| percent \| reported \| Higher is better \| \| `code_completion` \| 69.565 \| percent \| reported \| Higher is better \| \| `code_generation` \| 70.423 \| percent \| reported \| Higher is better \| \| `connections` \| 98 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 75.421 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 78 \| percent \| reported \| Higher is better \| \| `javascript` \| 54.545 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 64 \| percent \| reported \| Higher is better \| \| `math_comp` \| 96.078 \| percent \| reported \| Higher is better \| \| `olympiad` \| 90.624 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 56.217 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 56.391 \| percent \| reported \| Higher is better \| \| `python` \| 50 \| percent \| reported \| Higher is better \| \| `simplify` \| 55.933 \| percent \| reported \| Higher is better \| \| `spatial` \| 94 \| percent \| reported \| Higher is better \| \| `story_generation` \| 67.75 \| percent \| reported \| Higher is better \| \| `summarize` \| 69.5 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 48.192 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 100 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 80.769 \| percent \| reported \| Higher is better \| \| `typescript` \| 23.333 \| percent \| reported \| Higher is better \| \| `typos` \| 80 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 92 \| percent \| reported \| Higher is better \| ### Configuration Model configuration deepseek-v4-pro sourceRelease 2026_06_25 ### Source [Original source](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) Source LiveBench Original model label deepseek-v4-pro Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/8` | | | | | 1 | [GPT-5.2 Codex](https://benchize.com/models/gpt-5-2-codex.md) | 98% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `AMPS_Hard` \| 98 \| percent \| reported \| Higher is better \| \| `code_completion` \| 86.957 \| percent \| reported \| Higher is better \| \| `code_generation` \| 80.282 \| percent \| reported \| Higher is better \| \| `connections` \| 95 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 89.016 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 75 \| percent \| reported \| Higher is better \| \| `javascript` \| 68.182 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 68 \| percent \| reported \| Higher is better \| \| `math_comp` \| 95.098 \| percent \| reported \| Higher is better \| \| `olympiad` \| 86.997 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 67.05 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 56.035 \| percent \| reported \| Higher is better \| \| `python` \| 60 \| percent \| reported \| Higher is better \| \| `simplify` \| 60.567 \| percent \| reported \| Higher is better \| \| `spatial` \| 94 \| percent \| reported \| Higher is better \| \| `story_generation` \| 74.783 \| percent \| reported \| Higher is better \| \| `summarize` \| 63.383 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 45.596 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 100 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 78.846 \| percent \| reported \| Higher is better \| \| `typescript` \| 20 \| percent \| reported \| Higher is better \| \| `typos` \| 70 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 70 \| percent \| reported \| Higher is better \| ### Configuration Model configuration gpt-5.2-codex sourceRelease 2026_06_25 ### Source [Original source](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) Source LiveBench Original model label gpt-5.2-codex Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/13` | | | | | 6 | [Kimi K2.7 Code](https://benchize.com/models/kimi-k2-7-code.md) | 97% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `AMPS_Hard` \| 97 \| percent \| reported \| Higher is better \| \| `code_completion` \| 76.087 \| percent \| reported \| Higher is better \| \| `code_generation` \| 71.831 \| percent \| reported \| Higher is better \| \| `connections` \| 98 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 48.277 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 37 \| percent \| reported \| Higher is better \| \| `javascript` \| 63.636 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 74 \| percent \| reported \| Higher is better \| \| `math_comp` \| 94.118 \| percent \| reported \| Higher is better \| \| `olympiad` \| 90.299 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 48.533 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 55.717 \| percent \| reported \| Higher is better \| \| `python` \| 50 \| percent \| reported \| Higher is better \| \| `simplify` \| 49.75 \| percent \| reported \| Higher is better \| \| `spatial` \| 92 \| percent \| reported \| Higher is better \| \| `story_generation` \| 68.567 \| percent \| reported \| Higher is better \| \| `summarize` \| 58.317 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 47.538 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 92.157 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 69.231 \| percent \| reported \| Higher is better \| \| `typescript` \| 23.333 \| percent \| reported \| Higher is better \| \| `typos` \| 80 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 96 \| percent \| reported \| Higher is better \| ### Configuration Model configuration kimi-k2.7-code sourceRelease 2026_06_25 ### Source [Original source](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) Source LiveBench Original model label kimi-k2.7-code Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/23` | | | | | 6 | [Grok 4.3](https://benchize.com/models/grok-4-3.md) | 97% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `AMPS_Hard` \| 97 \| percent \| reported \| Higher is better \| \| `code_completion` \| 65.217 \| percent \| reported \| Higher is better \| \| `code_generation` \| 74.648 \| percent \| reported \| Higher is better \| \| `connections` \| 94 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 28.029 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 63 \| percent \| reported \| Higher is better \| \| `javascript` \| 27.273 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 66 \| percent \| reported \| Higher is better \| \| `math_comp` \| 95.098 \| percent \| reported \| Higher is better \| \| `olympiad` \| 82.258 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 64.383 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 48.74 \| percent \| reported \| Higher is better \| \| `python` \| 15 \| percent \| reported \| Higher is better \| \| `simplify` \| 57.6 \| percent \| reported \| Higher is better \| \| `spatial` \| 98 \| percent \| reported \| Higher is better \| \| `story_generation` \| 70.6 \| percent \| reported \| Higher is better \| \| `summarize` \| 58.417 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 41.25 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 98.039 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 61.538 \| percent \| reported \| Higher is better \| \| `typescript` \| 13.333 \| percent \| reported \| Higher is better \| \| `typos` \| 78 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 57.75 \| percent \| reported \| Higher is better \| ### Configuration Model configuration grok-4.3 sourceRelease 2026_06_25 ### Source [Original source](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) Source LiveBench Original model label grok-4.3 Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/20` | | | | | 8 | [Qwen3.6 27B](https://benchize.com/models/qwen3-6-27b.md) | 93% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `AMPS_Hard` \| 93 \| percent \| reported \| Higher is better \| \| `code_completion` \| 71.739 \| percent \| reported \| Higher is better \| \| `code_generation` \| 71.831 \| percent \| reported \| Higher is better \| \| `connections` \| 77.167 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 70.395 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 52 \| percent \| reported \| Higher is better \| \| `javascript` \| 54.545 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 62 \| percent \| reported \| Higher is better \| \| `math_comp` \| 92.157 \| percent \| reported \| Higher is better \| \| `olympiad` \| 82.317 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 49.433 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 42.746 \| percent \| reported \| Higher is better \| \| `python` \| 40 \| percent \| reported \| Higher is better \| \| `simplify` \| 50.733 \| percent \| reported \| Higher is better \| \| `spatial` \| 100 \| percent \| reported \| Higher is better \| \| `story_generation` \| 60.133 \| percent \| reported \| Higher is better \| \| `summarize` \| 52.617 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 42.846 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 98.039 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 65.385 \| percent \| reported \| Higher is better \| \| `typescript` \| 23.333 \| percent \| reported \| Higher is better \| \| `typos` \| 70 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 53.75 \| percent \| reported \| Higher is better \| ### Configuration Model configuration qwen3.6-27b sourceRelease 2026_06_25 ### Source [Original source](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) Source LiveBench Original model label qwen3.6-27b Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/25` | | | | | 9 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 75% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `AMPS_Hard` \| 75 \| percent \| reported \| Higher is better \| \| `code_completion` \| 67.391 \| percent \| reported \| Higher is better \| \| `code_generation` \| 69.014 \| percent \| reported \| Higher is better \| \| `connections` \| 96.333 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 84.614 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 56 \| percent \| reported \| Higher is better \| \| `javascript` \| 63.636 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 66 \| percent \| reported \| Higher is better \| \| `math_comp` \| 91.176 \| percent \| reported \| Higher is better \| \| `olympiad` \| 85.614 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 55.933 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 50.174 \| percent \| reported \| Higher is better \| \| `python` \| 35 \| percent \| reported \| Higher is better \| \| `simplify` \| 56.617 \| percent \| reported \| Higher is better \| \| `spatial` \| 94 \| percent \| reported \| Higher is better \| \| `story_generation` \| 63.55 \| percent \| reported \| Higher is better \| \| `summarize` \| 53.933 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 45.846 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 98.039 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 76.923 \| percent \| reported \| Higher is better \| \| `typescript` \| 23.333 \| percent \| reported \| Higher is better \| \| `typos` \| 84 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 61 \| percent \| reported \| Higher is better \| ### Configuration Model configuration minimax-m3 sourceRelease 2026_06_25 ### Source [Original source](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) Source LiveBench Original model label minimax-m3 Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/24` | | | | | 10 | [Grok Build 0 1](https://benchize.com/models/grok-build-0-1.md) | 66% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `AMPS_Hard` \| 66 \| percent \| reported \| Higher is better \| \| `code_completion` \| 67.391 \| percent \| reported \| Higher is better \| \| `code_generation` \| 63.38 \| percent \| reported \| Higher is better \| \| `connections` \| 84 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 69.728 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 66 \| percent \| reported \| Higher is better \| \| `javascript` \| 59.091 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 70 \| percent \| reported \| Higher is better \| \| `math_comp` \| 95.098 \| percent \| reported \| Higher is better \| \| `olympiad` \| 86.617 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 58.383 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 53.38 \| percent \| reported \| Higher is better \| \| `python` \| 45 \| percent \| reported \| Higher is better \| \| `simplify` \| 62.6 \| percent \| reported \| Higher is better \| \| `spatial` \| 98 \| percent \| reported \| Higher is better \| \| `story_generation` \| 72.533 \| percent \| reported \| Higher is better \| \| `summarize` \| 67.367 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 42.654 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 100 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 69.231 \| percent \| reported \| Higher is better \| \| `typescript` \| 33.333 \| percent \| reported \| Higher is better \| \| `typos` \| 80 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 68.25 \| percent \| reported \| Higher is better \| ### Configuration Model configuration grok-build-0.1 sourceRelease 2026_06_25 ### Source [Original source](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) Source LiveBench Original model label grok-build-0.1 Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/21` | | | | --- Cite as: LiveBench — Benchize, https://benchize.com/benchmarks/livebench%3Atasks (retrieved 2026-10-21)