Model comparison
GPT-4.1 vs Mistral Medium
GPT-4.1 and Mistral Medium score almost the same on the Noometry Index (35.9 vs 36.3), so choose on price, context window or the category you care about most.
Last verified . 30 shared benchmarks.
Mistral AISummary
- They share 30 benchmarks with published results for both. GPT-4.1 scores higher in 4 categories and Mistral Medium in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mistral Medium leads 24.0 to 11.7.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.6% for GPT-4.1 and 22.7% for Mistral Medium.
- Mistral Medium is cheaper at $1.50 / $7.50 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | Mistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 35.9 | 36.3 |
| Released | 2025-04-14 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 33K | 262K |
| Input $ / M tokens | $2 | $1.50 |
| Output $ / M tokens | $8 | $7.50 |
| Results tracked | 52 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4.1: 34.4 (#238), Mistral Medium: 34.2 (#243)
| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| WeirdML | 39% | 43.7% |
| LMArena Coding | 1391 | 1434 |
| ALE-Bench | 558.1 | 763.98 |
| SWE-bench Verified | 48.5% | — |
| FrontierCode | — | 8% |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| SciCode | — | 40.2% |
| CadEval | 42% | — |
Agentic & Tool Use GPT-4.1 leads
GPT-4.1: 34.7 (#43), Mistral Medium: 28.3 (#90)
| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | 37.7% |
Reasoning Mistral Medium leads
GPT-4.1: 11.7 (#339), Mistral Medium: 24.0 (#167)
| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 52.3% | 50% |
| LMArena Hard Prompts | 1384 | 1426 |
| DTBench | 68.3% | 75.5% |
| LMCA | 25.6% | 26.1% |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 0% |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 136.78 | — |
| ForecastBench | 61.5 | — |
Math Mistral Medium leads
GPT-4.1: 22.3 (#280), Mistral Medium: 28.1 (#245)
| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 38.3% | 32.2% |
| LMArena Math | 1370 | 1408 |
| MATH Level 5 | 83% | 81.6% |
| FrontierMath (Feb 2025 set) | 5.5% | 0.3% |
| FrontierMath (Tiers 1-3) | 6% | — |
| ProofBench | — | 9% |
| Omni-MATH | 47.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-4.1 leads
GPT-4.1: 37.1 (#160), Mistral Medium: 25.0 (#265)
| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| GPQA Diamond | 66.9% | 59.5% |
| Humanity's Last Exam | 5.4% | 4.5% |
| Vectara Hallucination Rate | 5.6% | 22.7% |
| LMArena Expert | 1364 | 1408 |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal GPT-4.1 leads
GPT-4.1: 38.2 (#67), Mistral Medium: 35.3 (#88)
| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| LMArena Vision | 1211 | 1172 |
| GeoBench | 72% | — |
Multilingual Mistral Medium leads
GPT-4.1: 49.4 (#133), Mistral Medium: 52.1 (#91)
| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1370 | 1408 |
| LMArena Chinese | 1382 | 1447 |
| LMArena French | 1382 | 1459 |
| LMArena German | 1381 | 1432 |
| LMArena Japanese | 1319 | 1378 |
| LMArena Korean | 1339 | 1380 |
| LMArena Russian | 1377 | 1411 |
| LMArena Spanish | 1376 | 1433 |
Instruction Following Mistral Medium leads
GPT-4.1: 71.3 (#153), Mistral Medium: 73.7 (#116)
| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1367 | 1398 |
| IFEval | 83.8% | — |
Long Context Mistral Medium leads
GPT-4.1: 40.0 (#163), Mistral Medium: 42.9 (#114)
| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1385 | 1406 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Mistral Medium leads
GPT-4.1: 57.6 (#125), Mistral Medium: 60.0 (#103)
| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| LMArena Text | 1383 | 1424 |
| LMArena Creative Writing | 1363 | 1391 |
| LMArena Multi-Turn | 1398 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than Mistral Medium?
GPT-4.1 and Mistral Medium score almost the same on the Noometry Index (35.9 vs 36.3), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-4.1 or Mistral Medium?
Mistral Medium is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or Mistral Medium better for coding?
They score almost the same on coding (34.4 vs 34.2); test both on your own repository before choosing.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 262K.
How many benchmarks do GPT-4.1 and Mistral Medium share?
30 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Mistral Medium has 36.