Skip to content

Benchmark

HMMT Feb 25

Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.

Models measured
11
Scores recorded
15
Sources
1
IQ weight
No weight published

Score distribution

95.4%
Mean
94.8%
Median
4.1%
Std dev
90.7%
10th percentile
100%
90th percentile
84.4%
Min
84.4%100%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1GPT-5.2 Prono tools · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.100%
2Step 3.5 FlashStep 3.5 technical report · Table 5 · PaCoRe· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.100%
3GPT 5.2no tools · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.99.4%
4DeepSeek V3.2 SpecialeSpeciale high-compute reasoning · temperature 1.0 · 128K context · pass@1· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.99.2%
5Step 3.5 FlashStep 3.5 technical report · Tables 12–13 · Python tool· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.98.7%
6Step 3.5 FlashStep 3.5 Flash official headline table · vanilla· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.98.4%
7Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.96.7%
8Qwen3.5 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.94.8%
9Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · with tools· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94.7%
10Nemotron 3 Super 120B A12Bofficial blog Figure 3 · rounded · tool setting not labeled· Reported by NVIDIA Developer· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94.7%
11Qwen3.6 27BQwen official release table · thinking mode unless benchmark requires otherwise· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.93.8%
12Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · no tools· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.93.7%
13DeepSeek V3.2Thinking mode · temperature 1.0 · 128K context · custom step-by-step / boxed-answer prompt· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.92.5%
14Qwen3.6 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.90.7%
15MiMo V2 FlashMiMo-V2-Flash final evaluation · February 2025· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.84.4%

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.