Model comparison
Llama 4 Maverick vs Mistral Small 3.1
Llama 4 Maverick and Mistral Small 3.1 score almost the same on the Noometry Index (30.9 vs 31.7), so choose on price, context window or the category you care about most.
Last verified . 27 shared benchmarks.
Meta
Mistral AISummary
- They share 27 benchmarks with published results for both. Llama 4 Maverick scores higher in 5 categories and Mistral Small 3.1 in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mistral Small 3.1 leads 38.3 to 26.6.
- The biggest single-benchmark swing is GPQA (HELM): 65% for Llama 4 Maverick and 39.2% for Mistral Small 3.1.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $0.35 / $0.56 for Mistral Small 3.1.
Side by side
| Llama 4 Maverick | Mistral Small 3.1 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.9 | 31.7 |
| Released | 2025-04-05 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 4K | 102K |
| Input $ / M tokens | $0.19 | $0.35 |
| Output $ / M tokens | $0.65 | $0.56 |
| Results tracked | 54 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
Llama 4 Maverick: 26.6 (#324), Mistral Small 3.1: 38.3 (#179)
| Benchmark | Llama 4 Maverick | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1302 | 1309 |
| 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 Small 3.1: —
| Benchmark | Llama 4 Maverick | Mistral Small 3.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning Mistral Small 3.1 leads
Llama 4 Maverick: 10.1 (#342), Mistral Small 3.1: 19.7 (#254)
| Benchmark | Llama 4 Maverick | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1281 | 1278 |
| Epoch Capabilities Index | 132.2 | 127.48 |
| 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 | — | 1% |
| EnigmaEval | 0.6% | — |
| DTBench | 61.9% | — |
| LMCA | 15.9% | — |
| ForecastBench | 57.5 | — |
Math Llama 4 Maverick leads
Llama 4 Maverick: 26.0 (#262), Mistral Small 3.1: 14.7 (#301)
| Benchmark | Llama 4 Maverick | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 20.6% | 3.9% |
| Omni-MATH | 42.2% | 24.8% |
| LMArena Math | 1299 | 1262 |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Llama 4 Maverick leads
Llama 4 Maverick: 33.4 (#204), Mistral Small 3.1: 22.6 (#271)
| Benchmark | Llama 4 Maverick | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 67% | 41.9% |
| MMLU-Pro | 81% | 61% |
| GPQA (HELM) | 65% | 39.2% |
| LMArena Expert | 1259 | 1257 |
| Humanity's Last Exam | 5.7% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
Multimodal Mistral Small 3.1 leads
Llama 4 Maverick: 31.6 (#105), Mistral Small 3.1: 33.2 (#99)
| Benchmark | Llama 4 Maverick | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | 1142 | 1136 |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Llama 4 Maverick leads
Llama 4 Maverick: 42.2 (#195), Mistral Small 3.1: 41.2 (#209)
| Benchmark | Llama 4 Maverick | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1269 | 1255 |
| LMArena Chinese | 1277 | 1253 |
| LMArena French | 1259 | 1273 |
| LMArena German | 1291 | 1266 |
| LMArena Japanese | 1207 | 1208 |
| LMArena Korean | 1203 | 1206 |
| LMArena Russian | 1286 | 1263 |
| LMArena Spanish | 1293 | 1283 |
Instruction Following Llama 4 Maverick leads
Llama 4 Maverick: 71.7 (#146), Mistral Small 3.1: 63.6 (#230)
| Benchmark | Llama 4 Maverick | Mistral Small 3.1 |
|---|---|---|
| IFEval | 90.8% | 75% |
| LMArena Instruction Following | 1267 | 1264 |
Long Context Mistral Small 3.1 leads
Llama 4 Maverick: 31.4 (#279), Mistral Small 3.1: 39.5 (#178)
| Benchmark | Llama 4 Maverick | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1280 | 1299 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Llama 4 Maverick leads
Llama 4 Maverick: 38.8 (#252), Mistral Small 3.1: 37.0 (#259)
| Benchmark | Llama 4 Maverick | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1287 | 1277 |
| LMArena Creative Writing | 1267 | 1253 |
| EQ-Bench Creative Writing | 860 | 761 |
| WildBench | 80% | 78.8% |
| LMArena Multi-Turn | 1289 | 1270 |
| Short-Story Creative Writing | 62% | — |
Frequently asked questions
Is Llama 4 Maverick better than Mistral Small 3.1?
Llama 4 Maverick and Mistral Small 3.1 score almost the same on the Noometry Index (30.9 vs 31.7), so choose on price, context window or the category you care about most.
Which is cheaper, Llama 4 Maverick or Mistral Small 3.1?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Mistral Small 3.1 lists at $0.35 and $0.56.
Is Llama 4 Maverick or Mistral Small 3.1 better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 26.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Llama 4 Maverick and Mistral Small 3.1 share?
27 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Mistral Small 3.1 has 28.