Model comparison
Llama 4 Maverick vs Mistral 7B
Llama 4 Maverick is the stronger model overall, scoring 30.9 to 23.0 on the Noometry Index.
Last verified . 23 shared benchmarks.
Meta
Mistral AISummary
- They share 23 benchmarks with published results for both. Llama 4 Maverick scores higher in 6 categories and Mistral 7B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 4 Maverick leads 33.4 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 73% for Llama 4 Maverick and 3.7% for Mistral 7B.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $0.19 / $0.65 for Llama 4 Maverick.
- Llama 4 Maverick accepts more context: 128K tokens versus 8K.
Side by side
| Llama 4 Maverick | Mistral 7B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.9 | 23.0 |
| Released | 2025-04-05 | 2023-09-27 |
| Weights | Open | Open |
| Context window | 128K | 8K |
| Max output | 4K | 8K |
| Input $ / M tokens | $0.19 | $0.25 |
| Output $ / M tokens | $0.65 | $0.25 |
| Results tracked | 54 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 4 Maverick: 26.6 (#324), Mistral 7B: 26.4 (#326)
| Benchmark | Llama 4 Maverick | Mistral 7B |
|---|---|---|
| BigCodeBench Instruct | 49.7% | 19.5% |
| LMArena Coding | 1302 | 1082 |
| BigCodeBench Complete | 61.4% | 27.3% |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| SciCode | 33.1% | — |
| WeirdML | 24.5% | — |
| ALE-Bench | 172.97 | — |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 28.2 (#91), Mistral 7B: —
| Benchmark | Llama 4 Maverick | Mistral 7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning Mistral 7B leads
Llama 4 Maverick: 10.1 (#342), Mistral 7B: 13.1 (#336)
| Benchmark | Llama 4 Maverick | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 1281 | 1067 |
| DTBench | 61.9% | 42.5% |
| Epoch Capabilities Index | 132.2 | 112.21 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| NYT Connections (extended) | 8% | — |
| ARC-AGI-1 | 4.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| EnigmaEval | 0.6% | — |
| LMCA | 15.9% | — |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| ForecastBench | 57.5 | — |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math Llama 4 Maverick leads
Llama 4 Maverick: 26.0 (#262), Mistral 7B: 8.1 (#325)
| Benchmark | Llama 4 Maverick | Mistral 7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 20.6% | 0.3% |
| LMArena Math | 1299 | 1085 |
| MATH Level 5 | 73% | 3.7% |
| Omni-MATH | 42.2% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
| GSM8K | — | 54.4% |
Knowledge Llama 4 Maverick leads
Llama 4 Maverick: 33.4 (#204), Mistral 7B: 7.4 (#311)
| Benchmark | Llama 4 Maverick | Mistral 7B |
|---|---|---|
| GPQA Diamond | 67% | 15.2% |
| LMArena Expert | 1259 | 1036 |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multimodal Not comparable
Llama 4 Maverick: 31.6 (#105), Mistral 7B: —
| Benchmark | Llama 4 Maverick | Mistral 7B |
|---|---|---|
| LMArena Vision | 1142 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Llama 4 Maverick leads
Llama 4 Maverick: 42.2 (#195), Mistral 7B: 25.8 (#283)
| Benchmark | Llama 4 Maverick | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1269 | 1012 |
| LMArena Chinese | 1277 | 1009 |
| LMArena French | 1259 | 1037 |
| LMArena German | 1291 | 987 |
| LMArena Japanese | 1207 | 878 |
| LMArena Russian | 1286 | 1018 |
| LMArena Spanish | 1293 | 1026 |
| LMArena Korean | 1203 | — |
Instruction Following Llama 4 Maverick leads
Llama 4 Maverick: 71.7 (#146), Mistral 7B: 54.2 (#280)
| Benchmark | Llama 4 Maverick | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1267 | 1060 |
| IFEval | 90.8% | — |
Long Context Too close to call
Llama 4 Maverick: 31.4 (#279), Mistral 7B: 32.2 (#271)
| Benchmark | Llama 4 Maverick | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1280 | 1060 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Llama 4 Maverick leads
Llama 4 Maverick: 38.8 (#252), Mistral 7B: 30.7 (#286)
| Benchmark | Llama 4 Maverick | Mistral 7B |
|---|---|---|
| LMArena Text | 1287 | 1090 |
| LMArena Creative Writing | 1267 | 1068 |
| LMArena Multi-Turn | 1289 | 1062 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Llama 4 Maverick better than Mistral 7B?
Llama 4 Maverick is the stronger model overall, scoring 30.9 to 23.0 on the Noometry Index.
Which is cheaper, Llama 4 Maverick or Mistral 7B?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Llama 4 Maverick lists at $0.19 and $0.65.
Is Llama 4 Maverick or Mistral 7B better for coding?
They score almost the same on coding (26.6 vs 26.4); test both on your own repository before choosing.
Which has the bigger context window?
Llama 4 Maverick does, with 128K tokens against 8K.
How many benchmarks do Llama 4 Maverick and Mistral 7B share?
23 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Mistral 7B has 37.