Model comparison
GPT-4.1 mini vs Mistral Large
GPT-4.1 mini is the stronger model overall, scoring 33.6 to 31.9 on the Noometry Index.
Last verified . 34 shared benchmarks.
Mistral AISummary
- They share 34 benchmarks with published results for both. GPT-4.1 mini scores higher in 6 categories and Mistral Large in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.1 mini leads 48.6 to 40.7.
- The biggest single-benchmark swing is MATH Level 5: 87.3% for GPT-4.1 mini and 50.3% for Mistral Large.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $2 / $6 for Mistral Large.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 mini | Mistral Large | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 33.6 | 31.9 |
| Released | 2025-04-14 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 33K | 16K |
| Input $ / M tokens | $0.40 | $2 |
| Output $ / M tokens | $1.60 | $6 |
| Results tracked | 47 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
GPT-4.1 mini: 30.6 (#293), Mistral Large: 34.3 (#240)
| Benchmark | GPT-4.1 mini | Mistral Large |
|---|---|---|
| SciCode | 40.4% | 36.2% |
| BigCodeBench Instruct | 48.9% | 30% |
| LMArena Coding | 1367 | 1277 |
| SWE-bench Verified (bash only) | 23.9% | — |
| Aider Polyglot | 32.4% | — |
| WeirdML | 37.6% | — |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| CadEval | 16% | — |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use GPT-4.1 mini leads
GPT-4.1 mini: 33.3 (#55), Mistral Large: 28.6 (#89)
| Benchmark | GPT-4.1 mini | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | 38.4% |
Reasoning Mistral Large leads
GPT-4.1 mini: 10.8 (#340), Mistral Large: 15.8 (#310)
| Benchmark | GPT-4.1 mini | Mistral Large |
|---|---|---|
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1349 | 1257 |
| DTBench | 68.8% | 65.1% |
| LMCA | 21.1% | 16.7% |
| Epoch Capabilities Index | 135.01 | 128.52 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 22.5% |
| Kagi LLM Benchmark | 48.6% | — |
| ARC-AGI-1 | 3.5% | — |
| Chess Puzzles | 7% | — |
| LiveBench Reasoning | — | 43.5% |
| Mystery Game Puzzles | 7% | — |
| LiveBench Data Analysis | — | 50.1% |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math GPT-4.1 mini leads
GPT-4.1 mini: 24.1 (#270), Mistral Large: 18.2 (#291)
| Benchmark | GPT-4.1 mini | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 44.7% | 8.5% |
| Omni-MATH | 49.1% | 28.1% |
| LMArena Math | 1343 | 1262 |
| MATH Level 5 | 87.3% | 50.3% |
| FrontierMath (Feb 2025 set) | 4.5% | 0.3% |
| FrontierMath (Tiers 1-3) | 6.7% | — |
| LiveBench Math | — | 42.5% |
Knowledge GPT-4.1 mini leads
GPT-4.1 mini: 34.7 (#194), Mistral Large: 30.1 (#230)
| Benchmark | GPT-4.1 mini | Mistral Large |
|---|---|---|
| GPQA Diamond | 65.8% | 51.3% |
| MMLU-Pro | 78.3% | 59.9% |
| GPQA (HELM) | 61.4% | 43.5% |
| LMArena Expert | 1338 | 1232 |
| SimpleQA Verified | 12.7% | — |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| MMLU | — | 80% |
Multimodal Not comparable
GPT-4.1 mini: 35.8 (#82), Mistral Large: —
| Benchmark | GPT-4.1 mini | Mistral Large |
|---|---|---|
| LMArena Vision | 1181 | — |
Multilingual GPT-4.1 mini leads
GPT-4.1 mini: 45.7 (#166), Mistral Large: 40.0 (#219)
| Benchmark | GPT-4.1 mini | Mistral Large |
|---|---|---|
| LMArena Non-English | 1318 | 1237 |
| LMArena Chinese | 1329 | 1240 |
| LMArena French | 1358 | 1325 |
| LMArena German | 1351 | 1254 |
| LMArena Japanese | 1290 | 1188 |
| LMArena Korean | 1298 | 1202 |
| LMArena Russian | 1324 | 1257 |
| LMArena Spanish | 1319 | 1268 |
Instruction Following GPT-4.1 mini leads
GPT-4.1 mini: 73.7 (#118), Mistral Large: 67.9 (#191)
| Benchmark | GPT-4.1 mini | Mistral Large |
|---|---|---|
| IFEval | 90.4% | 87.7% |
| LMArena Instruction Following | 1333 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
Long Context Mistral Large leads
GPT-4.1 mini: 31.8 (#275), Mistral Large: 38.3 (#199)
| Benchmark | GPT-4.1 mini | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1344 | 1261 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference GPT-4.1 mini leads
GPT-4.1 mini: 48.6 (#199), Mistral Large: 40.7 (#242)
| Benchmark | GPT-4.1 mini | Mistral Large |
|---|---|---|
| LMArena Text | 1340 | 1266 |
| LMArena Creative Writing | 1300 | 1243 |
| EQ-Bench Creative Writing | 1147 | 985 |
| WildBench | 83.8% | 80.1% |
| LMArena Multi-Turn | 1354 | 1260 |
| Short-Story Creative Writing | — | 69% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is GPT-4.1 mini better than Mistral Large?
GPT-4.1 mini is the stronger model overall, scoring 33.6 to 31.9 on the Noometry Index.
Which is cheaper, GPT-4.1 mini or Mistral Large?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Mistral Large lists at $2 and $6.
Is GPT-4.1 mini or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 mini does, with 1.05M tokens against 131K.
How many benchmarks do GPT-4.1 mini and Mistral Large share?
34 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Mistral Large has 51.