Model comparison
GPT-4.1 mini vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.0 to 33.5 on the Noometry Index. GPT-4.1 mini costs 4.3× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
Mistral AISummary
- They share 29 benchmarks with published results for both. GPT-4.1 mini scores higher in 3 categories and Mistral Medium in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mistral Medium leads 23.3 to 10.9.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 50.5% for GPT-4.1 mini and 37.7% for Mistral Medium.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- GPT-4.1 mini 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 mini | Mistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 33.5 | 36.0 |
| Released | 2025-04-14 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 33K | 262K |
| Input $ / M tokens | $0.40 | $1.50 |
| Output $ / M tokens | $1.60 | $7.50 |
| Results tracked | 47 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium leads
GPT-4.1 mini: 30.4 (#286), Mistral Medium: 33.8 (#241)
| Benchmark | GPT-4.1 mini | Mistral Medium |
|---|---|---|
| SciCode | 40.4% | 40.2% |
| WeirdML | 37.6% | 43.7% |
| LMArena Coding | 1367 | 1434 |
| FrontierCode | — | 8% |
| SWE-bench Verified (bash only) | 23.9% | — |
| Aider Polyglot | 32.4% | — |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use GPT-4.1 mini leads
GPT-4.1 mini: 33.0 (#52), Mistral Medium: 28.1 (#84)
| Benchmark | GPT-4.1 mini | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | 37.7% |
Reasoning Mistral Medium leads
GPT-4.1 mini: 10.9 (#335), Mistral Medium: 23.3 (#165)
| Benchmark | GPT-4.1 mini | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 48.6% | 50% |
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1349 | 1426 |
| DTBench | 68.8% | 75.5% |
| LMCA | 21.1% | 26.1% |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 3.5% | — |
| Chess Puzzles | 7% | — |
| Mystery Game Puzzles | 7% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 135.01 | — |
Math Mistral Medium leads
GPT-4.1 mini: 23.1 (#264), Mistral Medium: 27.2 (#238)
| Benchmark | GPT-4.1 mini | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 44.7% | 32.2% |
| LMArena Math | 1343 | 1409 |
| MATH Level 5 | 87.3% | 81.6% |
| FrontierMath (Feb 2025 set) | 4.5% | 0.3% |
| FrontierMath (Tiers 1-3) | 6.7% | — |
| ProofBench | — | 9% |
| Omni-MATH | 49.1% | — |
Knowledge GPT-4.1 mini leads
GPT-4.1 mini: 34.7 (#183), Mistral Medium: 24.9 (#260)
| Benchmark | GPT-4.1 mini | Mistral Medium |
|---|---|---|
| GPQA Diamond | 65.8% | 59.5% |
| LMArena Expert | 1338 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 12.7% | — |
| MMLU-Pro | 78.3% | — |
| Vectara Hallucination Rate | — | 22.7% |
| GPQA (HELM) | 61.4% | — |
Multimodal Too close to call
GPT-4.1 mini: 35.2 (#77), Mistral Medium: 34.6 (#82)
| Benchmark | GPT-4.1 mini | Mistral Medium |
|---|---|---|
| LMArena Vision | 1181 | 1172 |
Multilingual Mistral Medium leads
GPT-4.1 mini: 45.9 (#161), Mistral Medium: 52.3 (#86)
| Benchmark | GPT-4.1 mini | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1318 | 1408 |
| LMArena Chinese | 1329 | 1448 |
| LMArena French | 1357 | 1460 |
| LMArena German | 1349 | 1433 |
| LMArena Japanese | 1291 | 1378 |
| LMArena Korean | 1298 | 1382 |
| LMArena Russian | 1324 | 1411 |
| LMArena Spanish | 1319 | 1433 |
Instruction Following Too close to call
GPT-4.1 mini: 73.9 (#113), Mistral Medium: 73.9 (#111)
| Benchmark | GPT-4.1 mini | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1332 | 1398 |
| IFEval | 90.4% | — |
Long Context Mistral Medium leads
GPT-4.1 mini: 31.8 (#270), Mistral Medium: 42.9 (#108)
| Benchmark | GPT-4.1 mini | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1344 | 1406 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Mistral Medium leads
GPT-4.1 mini: 48.8 (#193), Mistral Medium: 60.2 (#97)
| Benchmark | GPT-4.1 mini | Mistral Medium |
|---|---|---|
| LMArena Text | 1341 | 1424 |
| LMArena Creative Writing | 1300 | 1391 |
| LMArena Multi-Turn | 1354 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 1147 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is GPT-4.1 mini better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.0 to 33.5 on the Noometry Index. GPT-4.1 mini costs 4.3× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 mini or Mistral Medium?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is GPT-4.1 mini or Mistral Medium better for coding?
Mistral Medium scores higher on coding benchmarks: 33.8 versus 30.4 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 mini does, with 1.05M tokens against 262K.
How many benchmarks do GPT-4.1 mini and Mistral Medium share?
29 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Mistral Medium has 36.