Model comparison
Llama 4 Maverick vs Mistral Large
Mistral Large is the stronger model overall, scoring 31.9 to 30.9 on the Noometry Index. Llama 4 Maverick costs 9.9× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.
Last verified . 41 shared benchmarks.
Meta
Mistral AISummary
- They share 41 benchmarks with published results for both. Llama 4 Maverick scores higher in 4 categories and Mistral Large in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 4 Maverick leads 26.0 to 18.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 61.4% for Llama 4 Maverick and 38.3% for Mistral Large.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $2 / $6 for Mistral Large.
- Mistral Large accepts more context: 131K tokens versus 128K.
Side by side
| Llama 4 Maverick | Mistral Large | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.9 | 31.9 |
| Released | 2025-04-05 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 16K |
| Input $ / M tokens | $0.19 | $2 |
| Output $ / M tokens | $0.65 | $6 |
| Results tracked | 54 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Llama 4 Maverick: 26.6 (#324), Mistral Large: 34.3 (#240)
| Benchmark | Llama 4 Maverick | Mistral Large |
|---|---|---|
| SciCode | 33.1% | 36.2% |
| BigCodeBench Instruct | 49.7% | 30% |
| LMArena Coding | 1302 | 1277 |
| BigCodeBench Complete | 61.4% | 38.3% |
| ALE-Bench | 172.97 | 264.7 |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| WeirdML | 24.5% | — |
| LiveBench Coding | — | 47.1% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Too close to call
Llama 4 Maverick: 28.2 (#91), Mistral Large: 28.6 (#89)
| Benchmark | Llama 4 Maverick | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | 38.4% |
Reasoning Mistral Large leads
Llama 4 Maverick: 10.1 (#342), Mistral Large: 15.8 (#310)
| Benchmark | Llama 4 Maverick | Mistral Large |
|---|---|---|
| SimpleBench | 27.7% | 22.5% |
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1281 | 1257 |
| DTBench | 61.9% | 65.1% |
| LMCA | 15.9% | 16.7% |
| Epoch Capabilities Index | 132.2 | 128.52 |
| ForecastBench | 57.5 | 57.1 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 55.9% | — |
| NYT Connections (extended) | 8% | — |
| ARC-AGI-1 | 4.4% | — |
| EnigmaEval | 0.6% | — |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| LiveBench | — | 48.4% |
Math Llama 4 Maverick leads
Llama 4 Maverick: 26.0 (#262), Mistral Large: 18.2 (#291)
| Benchmark | Llama 4 Maverick | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 20.6% | 8.5% |
| Omni-MATH | 42.2% | 28.1% |
| LMArena Math | 1299 | 1262 |
| MATH Level 5 | 73% | 50.3% |
| FrontierMath (Feb 2025 set) | 0.7% | 0.3% |
| LiveBench Math | — | 42.5% |
Knowledge Llama 4 Maverick leads
Llama 4 Maverick: 33.4 (#204), Mistral Large: 30.1 (#230)
| Benchmark | Llama 4 Maverick | Mistral Large |
|---|---|---|
| GPQA Diamond | 67% | 51.3% |
| MMLU-Pro | 81% | 59.9% |
| Confabulations | 22.6% | 21.4% |
| Vectara Hallucination Rate | 8.2% | 4.5% |
| GPQA (HELM) | 65% | 43.5% |
| LMArena Expert | 1259 | 1232 |
| Humanity's Last Exam | 5.7% | — |
| MMLU | — | 80% |
Multimodal Not comparable
Llama 4 Maverick: 31.6 (#105), Mistral Large: —
| Benchmark | Llama 4 Maverick | Mistral Large |
|---|---|---|
| LMArena Vision | 1142 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Llama 4 Maverick leads
Llama 4 Maverick: 42.2 (#195), Mistral Large: 40.0 (#219)
| Benchmark | Llama 4 Maverick | Mistral Large |
|---|---|---|
| LMArena Non-English | 1269 | 1237 |
| LMArena Chinese | 1277 | 1240 |
| LMArena French | 1259 | 1325 |
| LMArena German | 1291 | 1254 |
| LMArena Japanese | 1207 | 1188 |
| LMArena Korean | 1203 | 1202 |
| LMArena Russian | 1286 | 1257 |
| LMArena Spanish | 1293 | 1268 |
Instruction Following Llama 4 Maverick leads
Llama 4 Maverick: 71.7 (#146), Mistral Large: 67.9 (#191)
| Benchmark | Llama 4 Maverick | Mistral Large |
|---|---|---|
| IFEval | 90.8% | 87.7% |
| LMArena Instruction Following | 1267 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
Long Context Mistral Large leads
Llama 4 Maverick: 31.4 (#279), Mistral Large: 38.3 (#199)
| Benchmark | Llama 4 Maverick | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1280 | 1261 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Mistral Large leads
Llama 4 Maverick: 38.8 (#252), Mistral Large: 40.7 (#242)
| Benchmark | Llama 4 Maverick | Mistral Large |
|---|---|---|
| LMArena Text | 1287 | 1266 |
| LMArena Creative Writing | 1267 | 1243 |
| Short-Story Creative Writing | 62% | 69% |
| EQ-Bench Creative Writing | 860 | 985 |
| WildBench | 80% | 80.1% |
| LMArena Multi-Turn | 1289 | 1260 |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Llama 4 Maverick better than Mistral Large?
Mistral Large is the stronger model overall, scoring 31.9 to 30.9 on the Noometry Index. Llama 4 Maverick costs 9.9× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Maverick or Mistral Large?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Mistral Large lists at $2 and $6.
Is Llama 4 Maverick or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 26.6 in the Noometry coding category.
Which has the bigger context window?
Mistral Large does, with 131K tokens against 128K.
How many benchmarks do Llama 4 Maverick and Mistral Large share?
41 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Mistral Large has 51.