Model comparison
GPT-4.1 vs Mistral Large
GPT-4.1 is the stronger model overall, scoring 35.9 to 31.9 on the Noometry Index.
Last verified . 35 shared benchmarks.
Mistral AISummary
- They share 35 benchmarks with published results for both. GPT-4.1 scores higher in 8 categories and Mistral Large in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.1 leads 57.6 to 40.7.
- The biggest single-benchmark swing is MATH Level 5: 83% for GPT-4.1 and 50.3% for Mistral Large.
- Mistral Large is cheaper at $2 / $6 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 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 | Mistral Large | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 35.9 | 31.9 |
| Released | 2025-04-14 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 33K | 16K |
| Input $ / M tokens | $2 | $2 |
| Output $ / M tokens | $8 | $6 |
| Results tracked | 52 | 51 |
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 Large: 34.3 (#240)
| Benchmark | GPT-4.1 | Mistral Large |
|---|---|---|
| LMArena Coding | 1391 | 1277 |
| ALE-Bench | 558.1 | 264.7 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| SciCode | — | 36.2% |
| WeirdML | 39% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| CadEval | 42% | — |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use GPT-4.1 leads
GPT-4.1: 34.7 (#43), Mistral Large: 28.6 (#89)
| Benchmark | GPT-4.1 | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | 38.4% |
Reasoning Mistral Large leads
GPT-4.1: 11.7 (#339), Mistral Large: 15.8 (#310)
| Benchmark | GPT-4.1 | Mistral Large |
|---|---|---|
| SimpleBench | 27% | 22.5% |
| LMArena Hard Prompts | 1384 | 1257 |
| DTBench | 68.3% | 65.1% |
| LMCA | 25.6% | 16.7% |
| Epoch Capabilities Index | 136.78 | 128.52 |
| ForecastBench | 61.5 | 57.1 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 52.3% | — |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 0% |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| LiveBench | — | 48.4% |
Math GPT-4.1 leads
GPT-4.1: 22.3 (#280), Mistral Large: 18.2 (#291)
| Benchmark | GPT-4.1 | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 38.3% | 8.5% |
| Omni-MATH | 47.1% | 28.1% |
| LMArena Math | 1370 | 1262 |
| MATH Level 5 | 83% | 50.3% |
| FrontierMath (Feb 2025 set) | 5.5% | 0.3% |
| FrontierMath (Tiers 1-3) | 6% | — |
| LiveBench Math | — | 42.5% |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-4.1 leads
GPT-4.1: 37.1 (#160), Mistral Large: 30.1 (#230)
| Benchmark | GPT-4.1 | Mistral Large |
|---|---|---|
| GPQA Diamond | 66.9% | 51.3% |
| MMLU-Pro | 81.1% | 59.9% |
| Vectara Hallucination Rate | 5.6% | 4.5% |
| GPQA (HELM) | 65.9% | 43.5% |
| LMArena Expert | 1364 | 1232 |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| Confabulations | — | 21.4% |
| MMLU | — | 80% |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), Mistral Large: —
| Benchmark | GPT-4.1 | Mistral Large |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
Multilingual GPT-4.1 leads
GPT-4.1: 49.4 (#133), Mistral Large: 40.0 (#219)
| Benchmark | GPT-4.1 | Mistral Large |
|---|---|---|
| LMArena Non-English | 1370 | 1237 |
| LMArena Chinese | 1382 | 1240 |
| LMArena French | 1382 | 1325 |
| LMArena German | 1381 | 1254 |
| LMArena Japanese | 1319 | 1188 |
| LMArena Korean | 1339 | 1202 |
| LMArena Russian | 1377 | 1257 |
| LMArena Spanish | 1376 | 1268 |
Instruction Following GPT-4.1 leads
GPT-4.1: 71.3 (#153), Mistral Large: 67.9 (#191)
| Benchmark | GPT-4.1 | Mistral Large |
|---|---|---|
| IFEval | 83.8% | 87.7% |
| LMArena Instruction Following | 1367 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
Long Context GPT-4.1 leads
GPT-4.1: 40.0 (#163), Mistral Large: 38.3 (#199)
| Benchmark | GPT-4.1 | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1385 | 1261 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.6 (#125), Mistral Large: 40.7 (#242)
| Benchmark | GPT-4.1 | Mistral Large |
|---|---|---|
| LMArena Text | 1383 | 1266 |
| LMArena Creative Writing | 1363 | 1243 |
| EQ-Bench Creative Writing | 1420 | 985 |
| WildBench | 85.4% | 80.1% |
| LMArena Multi-Turn | 1398 | 1260 |
| Short-Story Creative Writing | — | 69% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is GPT-4.1 better than Mistral Large?
GPT-4.1 is the stronger model overall, scoring 35.9 to 31.9 on the Noometry Index.
Which is cheaper, GPT-4.1 or Mistral Large?
Mistral Large is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or Mistral Large better for coding?
They score almost the same on coding (34.4 vs 34.3); test both on your own repository before choosing.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 131K.
How many benchmarks do GPT-4.1 and Mistral Large share?
35 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Mistral Large has 51.