# GLM 5.3 FlashMax

> Source: Benchize (https://benchize.com) — https://benchize.com/models/glm-5-3-flash-max. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/glm-5-3-flash-max.

Z.ai

Canonical URL: https://benchize.com/models/glm-5-3-flash-max
Last updated: Thu, 22 Oct 2026 06:20:09 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Z.ai

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 94.28% | — | 12 / 144 | — | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### 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 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/15` |  |  |  |  |  |  |  |
| [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 31.83% | — | 97 / 125 | $1.15 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.3183 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.3567 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 1.1466 \| USD \| per_rollout \| Lower is better \| ### Configuration harness chisel Reasoning effort max sourceVersion v1_1 subset main ### Reported statistics flaggedRate 0 sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GLM 5.3 Flash Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GLM%205.3%20Flash/max/main` |  |  |  |  |  |  |  |
| [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 2,111.7 | Range 2,063–2,151.9 | 23 / 126 | — | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 2111.7 \| rating \| reported \| Higher is better \| \| `overall` \| 81.82 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 70.18 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 81.33 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 78.03 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 82.76 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 97.1 \| source_score \| rubric \| Higher is better \| \| `slop` \| 83.14 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 96.09 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 82.75 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 77.97 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 78.31 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 80.89 \| source_score \| rubric \| Higher is better \| ### Configuration provider openrouter Reasoning effort unknown scoreScope 10_task_current sourceConfiguration glm-5-3-flash-or thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 2,063–2,151.9 interval [2063,2151.9] rank 23 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label GLM-5.3 Flash (max) Evaluated 2026-10-08 Observed 2026-10-22T04:40:14.102Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/22` |  |  |  |  |  |  |  |
| [DeepSWE](https://benchize.com/benchmarks/deepswe%3Av1.1.md) | 63.39% | Range 59.01–67.77% | 30 / 70 | $0.48 | 1,537.8s | [deepswe](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.6339285714285714 \| score_fraction \| scored_rollout_attempts \| Higher is better \| \| `pass_at_4` \| 0.8495575221238938 \| score_fraction \| tasks_with_one_passing_rollout \| Higher is better \| \| `cost_per_attempt` \| 0.48196371245535713 \| USD \| scored_attempt \| Lower is better \| \| `duration` \| 1537.7995419129463 \| seconds \| scored_attempt \| Lower is better \| ### Configuration harness mini-swe-agent Reasoning effort max sourceConfiguration mini_swe_agent_glm_5_3_flash_max ### Reported statistics Uncertainty Reported interval: 59.01–67.77% interval [0.590148863911635,0.6777082789455078] intervalMethod 95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R)) runCount 4 sampleSize 448 taskCount 113 ### Source [Original source](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) Source deepswe Original model label glm-5-3-flash Observed 2026-10-22T03:50:05.889Z Evidence SHA-256 `a7c15d66288fd249c020b9931c017b92d1a3b90e480b3ff34974b752bd030019` Source locator `/rows/29` |  |  |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 91% | — | 65 / 245 | 0.04usd per task | — | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.91 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.0430698225 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup zai-glm-5-3-flash modelType CoT Reasoning effort max sourceModelVersion zai-glm-5-3-flash-max thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GLM-5.3-Flash (Max) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/250` |  |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 65.83% | — | 67 / 243 | 0.09usd per task | — | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6583333333333333 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.09331568458333339 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup zai-glm-5-3-flash modelType CoT Reasoning effort max sourceModelVersion zai-glm-5-3-flash-max thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GLM-5.3-Flash (Max) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/252` |  |  |  |  |  |  |  |
| [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 46.21% | — | 97 / 125 | $0.94 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4621 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.5108 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.9437 \| USD \| per_rollout \| Lower is better \| ### Configuration harness chisel Reasoning effort max sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GLM 5.3 Flash Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GLM%205.3%20Flash/max/extended` |  |  |  |  |  |  |  |

---
Cite as: GLM 5.3 FlashMax — Benchize, https://benchize.com/models/glm-5-3-flash-max (retrieved 2026-10-22)