Benchmark
MGSM
Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.
- Models and systems measured
- 31
- Scores recorded
- 32
- Sources
- 2
- IQ weight
- 2.25
Score distribution
- 81%
- Mean
- 86.4%
- Median
- 11.8%
- Std dev
- 58.7%
- 10th percentile
- 91.1%
- 90th percentile
- 53.1%
- Min
This benchmark has a weight of 2.25 for chat models, measured over 27 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 1 | Llama 4 Maverick· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 92.3% |
| 2 | o3 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 92% |
| 3 | Claude 3.5 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 91.6% |
| 4 | Llama 3.3 70B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 91.1% |
| 5 | O1 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 90.8% |
| 6 | Claude 3 Opus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 90.7% |
| 7 | Llama 4 Scout· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 90.6% |
| 8 | Llama 4 Scoutinstruction-tuned table· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 90.6% |
| 9 | GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 90.5% |
| 10 | o1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89.3% |
| 11 | GPT-4 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 88.5% |
| 12 | Gemini 1.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 87.5% |
| 13 | GPT-4o mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 87% |
| 14 | Llama 3.1 70B Instructmultilingual average· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 86.9% |
| 15 | Claude Haiku 3.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 85.6% |
| 16 | Qwen 3 235B A22B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 83.5% |
| 17 | Claude 3 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 83.5% |
| 18 | Gemini 1.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 82.6% |
| 19 | Phi 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.6% |
| 20 | Claude 3 Haiku· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 75.1% |
| 21 | GPT 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 74.5% |
| 22 | Llama 3.2 11B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 68.9% |
| 23 | Gemma 3n E4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 67% |
| 24 | Phi 4 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 63.9% |
| 25 | phi-3.5-moe-instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 58.7% |
| 26 | Llama 3.2 3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 58.2% |
| 27 | GPT-3.5 Turbo· LLM Stats data | 56.3% |
| 28 | Gemma 3n E2b It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 53.1% |
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| DeepSeek V4.1 Flash BaseEM · 8-shot· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 80.2% |
| Qwen3.7-Plus-BaseQwen3.8-Flash-Next release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 85.4% |
| Qwen3.8-27B-BaseQwen3.8-Flash-Next release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 86.4% |
| Qwen3.8-Flash-Next-BaseQwen3.8-Flash-Next release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 89.3% |
Data credits: Data by LLM Stats · 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.