Model comparison
Llama 4 Maverick vs Mistral
Llama 4 Maverick is the stronger model overall, scoring 30.9 to 29.9 on the Noometry Index.
Last verified . 22 shared benchmarks.
Meta
Mistral AISummary
- They share 22 benchmarks with published results for both. Llama 4 Maverick scores higher in 5 categories and Mistral in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 4 Maverick leads 71.7 to 52.6.
- The biggest single-benchmark swing is MMLU-Pro: 81% for Llama 4 Maverick and 27.7% for Mistral.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Maverick | Mistral | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.9 | 29.9 |
| Released | 2025-04-05 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.19 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 54 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Llama 4 Maverick: 26.6 (#324), Mistral: 33.8 (#250)
| Benchmark | Llama 4 Maverick | Mistral |
|---|---|---|
| LMArena Coding | 1302 | 1162 |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| SciCode | 33.1% | — |
| WeirdML | 24.5% | — |
| BigCodeBench Instruct | 49.7% | — |
| BigCodeBench Complete | 61.4% | — |
| ALE-Bench | 172.97 | — |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 28.2 (#91), Mistral: —
| Benchmark | Llama 4 Maverick | Mistral |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning Mistral leads
Llama 4 Maverick: 10.1 (#342), Mistral: 22.2 (#200)
| Benchmark | Llama 4 Maverick | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1281 | 1149 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| NYT Connections (extended) | 8% | — |
| ARC-AGI-1 | 4.4% | — |
| CritPt | 0% | — |
| EnigmaEval | 0.6% | — |
| DTBench | 61.9% | — |
| LMCA | 15.9% | — |
| Epoch Capabilities Index | 132.2 | — |
| ForecastBench | 57.5 | — |
Math Llama 4 Maverick leads
Llama 4 Maverick: 26.0 (#262), Mistral: 22.3 (#278)
| Benchmark | Llama 4 Maverick | Mistral |
|---|---|---|
| Omni-MATH | 42.2% | 7.2% |
| LMArena Math | 1299 | 1180 |
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Llama 4 Maverick leads
Llama 4 Maverick: 33.4 (#204), Mistral: 16.6 (#288)
| Benchmark | Llama 4 Maverick | Mistral |
|---|---|---|
| MMLU-Pro | 81% | 27.7% |
| GPQA (HELM) | 65% | 30.3% |
| LMArena Expert | 1259 | 1125 |
| GPQA Diamond | 67% | — |
| Humanity's Last Exam | 5.7% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
Multimodal Not comparable
Llama 4 Maverick: 31.6 (#105), Mistral: —
| Benchmark | Llama 4 Maverick | Mistral |
|---|---|---|
| LMArena Vision | 1142 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Llama 4 Maverick leads
Llama 4 Maverick: 42.2 (#195), Mistral: 32.8 (#254)
| Benchmark | Llama 4 Maverick | Mistral |
|---|---|---|
| LMArena Non-English | 1269 | 1129 |
| LMArena Chinese | 1277 | 1109 |
| LMArena French | 1259 | 1180 |
| LMArena German | 1291 | 1155 |
| LMArena Japanese | 1207 | 1013 |
| LMArena Korean | 1203 | 1032 |
| LMArena Russian | 1286 | 1168 |
| LMArena Spanish | 1293 | 1143 |
Instruction Following Llama 4 Maverick leads
Llama 4 Maverick: 71.7 (#146), Mistral: 52.6 (#288)
| Benchmark | Llama 4 Maverick | Mistral |
|---|---|---|
| IFEval | 90.8% | 56.8% |
| LMArena Instruction Following | 1267 | 1152 |
Long Context Mistral leads
Llama 4 Maverick: 31.4 (#279), Mistral: 35.0 (#245)
| Benchmark | Llama 4 Maverick | Mistral |
|---|---|---|
| LMArena Longer Query | 1280 | 1153 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Llama 4 Maverick leads
Llama 4 Maverick: 38.8 (#252), Mistral: 37.0 (#260)
| Benchmark | Llama 4 Maverick | Mistral |
|---|---|---|
| LMArena Text | 1287 | 1165 |
| LMArena Creative Writing | 1267 | 1158 |
| WildBench | 80% | 66% |
| LMArena Multi-Turn | 1289 | 1147 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
Frequently asked questions
Is Llama 4 Maverick better than Mistral?
Llama 4 Maverick is the stronger model overall, scoring 30.9 to 29.9 on the Noometry Index.
Is Llama 4 Maverick or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 26.6 in the Noometry coding category.
How many benchmarks do Llama 4 Maverick and Mistral share?
22 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Mistral has 22.