Model comparison
Claude Opus 4 vs Mistral Large 3
Claude Opus 4 is the stronger model overall, scoring 42.9 to 38.6 on the Noometry Index. Mistral Large 3 costs 80× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. Claude Opus 4 scores higher in 6 categories and Mistral Large 3 in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Opus 4 leads 47.8 to 34.1.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 74.3% for Claude Opus 4 and 50.9% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- Mistral Large 3 accepts more context: 262K tokens versus 200K.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4 | Mistral Large 3 | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 42.9 | 38.6 |
| Released | 2025-05-22 | 2025-12-02 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 32K | 8K |
| Input $ / M tokens | $15 | $0.25 |
| Output $ / M tokens | $75 | $0.75 |
| Results tracked | 56 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude Opus 4: 47.8 (#55), Mistral Large 3: 34.1 (#230)
| Benchmark | Claude Opus 4 | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1442 | 1447 |
| SWE-bench Verified | 70.7% | — |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1230 |
| GSO | 6.9% | — |
| WeirdML | 43.7% | — |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Not comparable
Claude Opus 4: 34.5 (#39), Mistral Large 3: —
| Benchmark | Claude Opus 4 | Mistral Large 3 |
|---|---|---|
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning Claude Opus 4 leads
Claude Opus 4: 27.4 (#104), Mistral Large 3: 14.6 (#314)
| Benchmark | Claude Opus 4 | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 74.3% | 50.9% |
| LMArena Hard Prompts | 1399 | 1429 |
| ARC-AGI-2 | 8.6% | — |
| SimpleBench | 58.8% | — |
| NYT Connections (extended) | — | 7.5% |
| ARC-AGI-1 | 35.7% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 5.6% | — |
| Thematic Generalization | — | 23% |
| DTBench | 81.6% | — |
| LMCA | 37.4% | — |
| Epoch Capabilities Index | 142.67 | — |
| ForecastBench | 61.1 | — |
Math Claude Opus 4 leads
Claude Opus 4: 40.2 (#80), Mistral Large 3: 36.0 (#131)
| Benchmark | Claude Opus 4 | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1391 | 1415 |
| OTIS Mock AIME 2024-2025 | 64.4% | — |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4 leads
Claude Opus 4: 43.9 (#82), Mistral Large 3: 35.5 (#173)
| Benchmark | Claude Opus 4 | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 12% | 14.5% |
| LMArena Expert | 1384 | 1421 |
| GPQA Diamond | 76.3% | — |
| Humanity's Last Exam | 10.7% | — |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Mistral Large 3 leads
Claude Opus 4: 30.9 (#101), Mistral Large 3: 37.6 (#65)
| Benchmark | Claude Opus 4 | Mistral Large 3 |
|---|---|---|
| LMArena Vision | 1192 | 1222 |
| GeoBench | 49% | — |
| VPCT | 38% | — |
Multilingual Mistral Large 3 leads
Claude Opus 4: 49.0 (#133), Mistral Large 3: 52.6 (#79)
| Benchmark | Claude Opus 4 | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1362 | 1412 |
| LMArena Chinese | 1386 | 1448 |
| LMArena French | 1370 | 1456 |
| LMArena German | 1391 | 1438 |
| LMArena Japanese | 1332 | 1399 |
| LMArena Korean | 1318 | 1384 |
| LMArena Russian | 1392 | 1412 |
| LMArena Spanish | 1388 | 1437 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.3 (#26), Mistral Large 3: 74.1 (#104)
| Benchmark | Claude Opus 4 | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1402 |
| IFEval | 91.8% | — |
Long Context Mistral Large 3 leads
Claude Opus 4: 39.5 (#167), Mistral Large 3: 43.1 (#102)
| Benchmark | Claude Opus 4 | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1422 | 1413 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Claude Opus 4 leads
Claude Opus 4: 61.4 (#85), Mistral Large 3: 60.2 (#100)
| Benchmark | Claude Opus 4 | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1377 | 1427 |
| LMArena Creative Writing | 1386 | 1385 |
| EQ-Bench Creative Writing | 1580 | 1412 |
| LMArena Multi-Turn | 1396 | 1429 |
| Short-Story Creative Writing | 83.6% | — |
| WildBench | 85.2% | — |
Frequently asked questions
Is Claude Opus 4 better than Mistral Large 3?
Claude Opus 4 is the stronger model overall, scoring 42.9 to 38.6 on the Noometry Index. Mistral Large 3 costs 80× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4 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; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or Mistral Large 3 better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.8 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 200K.
How many benchmarks do Claude Opus 4 and Mistral Large 3 share?
21 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Mistral Large 3 has 24.