MATH
AI benchmark results and model performance
Type: percentage
Recorded results
88
Average score
63.49%
Score range
12.40% - 97.90%
Leading model
97.90% - o3 mini
Scores over time
Individual benchmark scores plotted by date.
Model results
| Organisation | Models | Reported | Top score | Info | Self reported | Source |
|---|---|---|---|---|---|---|
| o3 mini | 30 Jan 2025 | 97.90% | - | Yes | Source | |
| Ministral 3.0 14B | 02 Dec 2025 | 90.40% | Majority @ 1 | Yes | Source | |
| Gemini 2.0 Flash | 05 Feb 2025 | 89.70% | - | Yes | Source | |
| Gemini 2.0 Flash Exp | - | 89.70% | inferred alias from gemini-2.0-flash | Yes | Source | |
| Gemini 2.0 Pro Exp (2025-02-05) | 05 Feb 2025 | 89.70% | inferred modality/version alias from gemini-2.0-flash | Yes | Source | |
| LearnLM 2.0 Flash Experimental | 17 Apr 2025 | 89.70% | inferred family alias from gemini-2.0-flash (score=0.3700; benches=13) | Yes | Source | |
| Ministral 3.0 8B | 02 Dec 2025 | 87.60% | Majority @ 1 | Yes | Source | |
| Gemini 2.0 Flash Lite | 05 Feb 2025 | 86.80% | - | Yes | Source | |
| Gemini 1.5 Pro 001 | 23 May 2024 | 86.50% | inferred alias from gemini-1.5-pro | Yes | Source | |
| Gemini 1.5 Pro Exp (2024-08-01) | 01 Aug 2024 | 86.50% | inferred alias from gemini-1.5-pro | Yes | Source | |
| Gemini 1.5 Pro Exp (2024-08-27) | 27 Aug 2024 | 86.50% | inferred alias from gemini-1.5-pro | Yes | Source | |
| Gemini Robotics ER 1.5 Preview | 25 Sept 2025 | 86.50% | inferred family alias from gemini-1.5-pro (score=0.3717; benches=23) | Yes | Source | |
| LearnLM 1.5 Pro Experimental | 19 Nov 2024 | 86.50% | inferred family alias from gemini-1.5-pro (score=0.3700; benches=23) | Yes | Source | |
| o1 preview | 12 Sept 2024 | 85.50% | - | Yes | Source | |
| Qwen 72B | - | 83.10% | inferred family alias from qwen-2.5-72b-instruct (score=0.3060; benches=14) | Yes | Source | |
| Ministral 3.0 3B | 02 Dec 2025 | 83% | Majority @ 1 | Yes | Source | |
| Qwen 2.5 Coder 32B Instruct | - | 82.20% | inferred high-confidence family alias from qwen2.5-vl-32b (score=0.4641; benches=28) | Yes | Source | |
| Qwen 2.5 VL 32B Instruct | 24 Mar 2025 | 82.20% | - | Yes | Source | |
| Qwen 2.5 VL 3B Instruct | - | 82.20% | inferred high-confidence family alias from qwen2.5-vl-32b (score=0.4914; benches=28) | Yes | Source | |
| Phi 1 | - | 80.40% | inferred family alias from phi-4 (score=0.3100; benches=13) | Yes | Source | |
| Phi 2 | - | 80.40% | inferred family alias from phi-4 (score=0.3100; benches=13) | Yes | Source | |
| Phi 4 | 12 Dec 2024 | 80.40% | - | Yes | Source | |
| Qwen 14B | - | 80% | inferred family alias from qwen-2.5-14b-instruct (score=0.3060; benches=16) | Yes | Source | |
| Gemini 1.5 Flash 001 | 23 May 2024 | 77.90% | inferred alias from gemini-1.5-flash | Yes | Source | |
| Gemini 1.5 Flash Preview | 14 May 2024 | 77.90% | inferred alias from gemini-1.5-flash | Yes | Source |
