Skip to content

Benchmark

AIME26

Scores are percentages. Higher is better.

Models measured
11
Scores recorded
12
Sources
1
IQ weight
0.99

Score distribution

93.5%
Mean
94.1%
Median
2.9%
Std dev
89.2%
10th percentile
96.4%
90th percentile
88.3%
Min
88.3%99.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.99 for chat models, measured over 11 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GLM 5.2GPT-5.5 medium judge· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.99.2%
2Kimi K2.6Kimi K2.6 official benchmark table · thinking · temp 1.0 · top_p 1.0 · 262,144 context· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.96.4%
3GLM 5.1GLM-5.1 official release table · full AIME 2026· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.95.3%
4Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise · full AIME 2026 I + II· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.95.3%
5Muse Glimmer 30Bhigh reasoning· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94.7%
6Qwen3.6 27BQwen official release table · thinking mode unless benchmark requires otherwise · full AIME 2026 I + II· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94.1%
7Kimi K2.6Kimi K2.6 official launch blog · headline comparison table· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.93.3%
8GLM 5GLM-5 official release table · AIME 2026 I· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.92.7%
9Qwen3.6 FlashQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.92.7%
10Qwen3.5 397B A17BQwen3.5 release/model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.91.3%
11Gemma 4 31B ITGemma 4 Technical Report · Table 5 · thinking mode unless noted · no tools· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.89.2%
12Gemma 4 26B A4BGemma 4 Technical Report · Table 5 · thinking mode unless noted · no tools· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.88.3%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.