Model comparison
GPT-4.1 nano vs Mistral
Mistral is the stronger model overall, scoring 29.4 to 27.7 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AISummary
- They share 19 benchmarks with published results for both. GPT-4.1 nano scores higher in 5 categories and Mistral in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-4.1 nano leads 68.0 to 52.9.
- The biggest single-benchmark swing is Omni-MATH: 36.7% for GPT-4.1 nano and 7.2% for Mistral.
Side by side
| GPT-4.1 nano | Mistral | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 27.7 | 29.4 |
| Released | 2025-04-14 | — |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 38 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
GPT-4.1 nano: 23.8 (#325), Mistral: 33.2 (#249)
| Benchmark | GPT-4.1 nano | Mistral |
|---|---|---|
| LMArena Coding | 1306 | 1162 |
| Aider Polyglot | 8.9% | — |
| SciCode | 25.9% | — |
| WeirdML | 19% | — |
Agentic & Tool Use Not comparable
GPT-4.1 nano: 26.3 (#98), Mistral: —
| Benchmark | GPT-4.1 nano | Mistral |
|---|---|---|
| Berkeley Function Calling Leaderboard | 33% | — |
Reasoning Mistral leads
GPT-4.1 nano: 8.6 (#344), Mistral: 21.3 (#199)
| Benchmark | GPT-4.1 nano | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1286 | 1149 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 33.3% | — |
| ARC-AGI-1 | 0% | — |
| CritPt | 0% | — |
| DTBench | 52.5% | — |
| LMCA | 5.5% | — |
| Epoch Capabilities Index | 129.62 | — |
Math GPT-4.1 nano leads
GPT-4.1 nano: 25.5 (#246), Mistral: 20.5 (#275)
| Benchmark | GPT-4.1 nano | Mistral |
|---|---|---|
| Omni-MATH | 36.7% | 7.2% |
| LMArena Math | 1274 | 1180 |
| OTIS Mock AIME 2024-2025 | 28.9% | — |
| MATH Level 5 | 70% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
Knowledge GPT-4.1 nano leads
GPT-4.1 nano: 21.8 (#268), Mistral: 16.3 (#283)
| Benchmark | GPT-4.1 nano | Mistral |
|---|---|---|
| MMLU-Pro | 55% | 27.7% |
| GPQA (HELM) | 50.7% | 30.3% |
| LMArena Expert | 1272 | 1125 |
| GPQA Diamond | 48.9% | — |
| SimpleQA Verified | 6% | — |
Multimodal Not comparable
GPT-4.1 nano: 28.6 (#108), Mistral: —
| Benchmark | GPT-4.1 nano | Mistral |
|---|---|---|
| LMArena Vision | 1063 | — |
Multilingual GPT-4.1 nano leads
GPT-4.1 nano: 41.8 (#200), Mistral: 33.0 (#249)
| Benchmark | GPT-4.1 nano | Mistral |
|---|---|---|
| LMArena Non-English | 1260 | 1129 |
| LMArena Chinese | 1270 | 1109 |
| LMArena German | 1288 | 1155 |
| LMArena Japanese | 1199 | 1012 |
| LMArena Russian | 1261 | 1168 |
| LMArena French | — | 1179 |
| LMArena Korean | — | 1032 |
| LMArena Spanish | — | 1143 |
Instruction Following GPT-4.1 nano leads
GPT-4.1 nano: 68.0 (#188), Mistral: 52.9 (#283)
| Benchmark | GPT-4.1 nano | Mistral |
|---|---|---|
| IFEval | 84.3% | 56.8% |
| LMArena Instruction Following | 1267 | 1152 |
Long Context Mistral leads
GPT-4.1 nano: 23.7 (#291), Mistral: 35.0 (#240)
| Benchmark | GPT-4.1 nano | Mistral |
|---|---|---|
| LMArena Longer Query | 1283 | 1154 |
| Fiction.LiveBench | 25% | — |
Writing & Preference GPT-4.1 nano leads
GPT-4.1 nano: 40.7 (#238), Mistral: 37.2 (#255)
| Benchmark | GPT-4.1 nano | Mistral |
|---|---|---|
| LMArena Text | 1285 | 1165 |
| LMArena Creative Writing | 1260 | 1158 |
| WildBench | 81.2% | 66% |
| LMArena Multi-Turn | 1277 | 1147 |
| EQ-Bench Creative Writing | 946 | — |
Frequently asked questions
Is GPT-4.1 nano better than Mistral?
Mistral is the stronger model overall, scoring 29.4 to 27.7 on the Noometry Index.
Is GPT-4.1 nano or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.2 versus 23.8 in the Noometry coding category.
How many benchmarks do GPT-4.1 nano and Mistral share?
19 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and Mistral has 22.