Model comparison
GPT-5.2 Pro vs Mistral
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 29.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in math, where GPT-5.2 Pro leads 65.3 to 22.3.
Side by side
| GPT-5.2 Pro | Mistral | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 52.3 | 29.9 |
| Released | 2025-12-11 | — |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $21 | — |
| Output $ / M tokens | $168 | — |
| Results tracked | 8 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.2 Pro: —, Mistral: 33.8 (#250)
| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| LMArena Coding | — | 1162 |
Reasoning GPT-5.2 Pro leads
GPT-5.2 Pro: 51.5 (#33), Mistral: 22.2 (#200)
| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| ARC-AGI-2 | 54.2% | — |
| SimpleBench | 57.4% | — |
| NYT Connections (extended) | 79.3% | — |
| ARC-AGI-1 | 90.5% | — |
| LMArena Hard Prompts | — | 1149 |
| Epoch Capabilities Index | 155.4 | — |
Math GPT-5.2 Pro leads
GPT-5.2 Pro: 65.3 (#29), Mistral: 22.3 (#278)
| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| Omni-MATH | — | 7.2% |
| LMArena Math | — | 1180 |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge Not comparable
GPT-5.2 Pro: —, Mistral: 16.6 (#288)
| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |
Multilingual Not comparable
GPT-5.2 Pro: —, Mistral: 32.8 (#254)
| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| LMArena Non-English | — | 1129 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1180 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |
| LMArena Russian | — | 1168 |
| LMArena Spanish | — | 1143 |
Instruction Following Not comparable
GPT-5.2 Pro: —, Mistral: 52.6 (#288)
| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| IFEval | — | 56.8% |
| LMArena Instruction Following | — | 1152 |
Long Context Not comparable
GPT-5.2 Pro: —, Mistral: 35.0 (#245)
| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| LMArena Longer Query | — | 1153 |
Writing & Preference Not comparable
GPT-5.2 Pro: —, Mistral: 37.0 (#260)
| Benchmark | GPT-5.2 Pro | Mistral |
|---|---|---|
| LMArena Text | — | 1165 |
| LMArena Creative Writing | — | 1158 |
| WildBench | — | 66% |
| LMArena Multi-Turn | — | 1147 |
Frequently asked questions
Is GPT-5.2 Pro better than Mistral?
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 29.9 on the Noometry Index.
How many benchmarks do GPT-5.2 Pro and Mistral share?
0 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Mistral has 22.