Model comparison
GPT-4.1 vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 35.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. GPT-4.1 scores higher in 1 category and Mistral Large 3 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large 3 leads 38.7 to 22.3.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.6% for GPT-4.1 and 14.5% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 262K.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | Mistral Large 3 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 35.9 | 39.1 |
| Released | 2025-04-14 | 2025-12-02 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 33K | 8K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $8 | $0.75 |
| Results tracked | 52 | 24 |
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 3: 34.4 (#237)
| Benchmark | GPT-4.1 | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1391 | 1448 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| LMArena WebDev | — | 1230 |
| WeirdML | 39% | — |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
Agentic & Tool Use Not comparable
GPT-4.1: 34.7 (#43), Mistral Large 3: —
| Benchmark | GPT-4.1 | Mistral Large 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning Mistral Large 3 leads
GPT-4.1: 11.7 (#339), Mistral Large 3: 15.2 (#319)
| Benchmark | GPT-4.1 | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 52.3% | 50.9% |
| LMArena Hard Prompts | 1384 | 1429 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| NYT Connections (extended) | — | 7.5% |
| ARC-AGI-1 | 5.5% | — |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| Thematic Generalization | — | 23% |
| DTBench | 68.3% | — |
| LMCA | 25.6% | — |
| Epoch Capabilities Index | 136.78 | — |
| ForecastBench | 61.5 | — |
Math Mistral Large 3 leads
GPT-4.1: 22.3 (#280), Mistral Large 3: 38.7 (#129)
| Benchmark | GPT-4.1 | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1370 | 1414 |
| FrontierMath (Tiers 1-3) | 6% | — |
| OTIS Mock AIME 2024-2025 | 38.3% | — |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-4.1 leads
GPT-4.1: 37.1 (#160), Mistral Large 3: 36.0 (#177)
| Benchmark | GPT-4.1 | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 5.6% | 14.5% |
| LMArena Expert | 1364 | 1421 |
| GPQA Diamond | 66.9% | — |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal Too close to call
GPT-4.1: 38.2 (#67), Mistral Large 3: 38.2 (#66)
| Benchmark | GPT-4.1 | Mistral Large 3 |
|---|---|---|
| LMArena Vision | 1211 | 1221 |
| GeoBench | 72% | — |
Multilingual Mistral Large 3 leads
GPT-4.1: 49.4 (#133), Mistral Large 3: 52.5 (#84)
| Benchmark | GPT-4.1 | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1370 | 1413 |
| LMArena Chinese | 1382 | 1447 |
| LMArena French | 1382 | 1455 |
| LMArena German | 1381 | 1437 |
| LMArena Japanese | 1319 | 1394 |
| LMArena Korean | 1339 | 1384 |
| LMArena Russian | 1377 | 1411 |
| LMArena Spanish | 1376 | 1440 |
Instruction Following Mistral Large 3 leads
GPT-4.1: 71.3 (#153), Mistral Large 3: 74.0 (#108)
| Benchmark | GPT-4.1 | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1367 | 1403 |
| IFEval | 83.8% | — |
Long Context Mistral Large 3 leads
GPT-4.1: 40.0 (#163), Mistral Large 3: 43.1 (#105)
| Benchmark | GPT-4.1 | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1385 | 1413 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Mistral Large 3 leads
GPT-4.1: 57.6 (#125), Mistral Large 3: 60.0 (#101)
| Benchmark | GPT-4.1 | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1383 | 1428 |
| LMArena Creative Writing | 1363 | 1386 |
| EQ-Bench Creative Writing | 1420 | 1412 |
| LMArena Multi-Turn | 1398 | 1429 |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 35.9 on the Noometry Index.
Which is cheaper, GPT-4.1 or Mistral Large 3?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or Mistral Large 3 better for coding?
They score almost the same on coding (34.4 vs 34.4); 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 Large 3 share?
21 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Mistral Large 3 has 24.