Model comparison
Kimi K3 vs Mistral Small 3.1
Kimi K3 is the stronger model overall, scoring 59.5 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 15× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. Kimi K3 scores higher in 9 categories and Mistral Small 3.1 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.2 to 14.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 97.2% for Kimi K3 and 3.9% for Mistral Small 3.1.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 128K.
Side by side
| Kimi K3 | Mistral Small 3.1 | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 59.5 | 31.7 |
| Released | 2026-07-16 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 1.05M | 128K |
| Max output | 1.05M | 102K |
| Input $ / M tokens | $3 | $0.35 |
| Output $ / M tokens | $15 | $0.56 |
| Results tracked | 53 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), Mistral Small 3.1: 38.3 (#179)
| Benchmark | Kimi K3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1508 | 1309 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| SciCode | 59.5% | — |
| WeirdML | 82.6% | — |
| ALE-Bench | 1,524 | — |
Agentic & Tool Use Not comparable
Kimi K3: 41.8 (#20), Mistral Small 3.1: —
| Benchmark | Kimi K3 | Mistral Small 3.1 |
|---|---|---|
| APEX-Agents | 50.6% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 32% | — |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), Mistral Small 3.1: 19.7 (#254)
| Benchmark | Kimi K3 | Mistral Small 3.1 |
|---|---|---|
| Chess Puzzles | 39% | 1% |
| LMArena Hard Prompts | 1496 | 1278 |
| Epoch Capabilities Index | 157.45 | 127.48 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 23.4% | — |
| Mystery Game Puzzles | 26% | — |
| DTBench | 91.2% | — |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
| ForecastBench | 61.1 | — |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Mistral Small 3.1: 14.7 (#301)
| Benchmark | Kimi K3 | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 97.2% | 3.9% |
| LMArena Math | 1491 | 1262 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| ProofBench | 87% | — |
| Omni-MATH | — | 24.8% |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), Mistral Small 3.1: 22.6 (#271)
| Benchmark | Kimi K3 | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 93.1% | 41.9% |
| LMArena Expert | 1521 | 1257 |
| SimpleQA Verified | 50.6% | — |
| MMLU-Pro | — | 61% |
| GPQA (HELM) | — | 39.2% |
Multimodal Kimi K3 leads
Kimi K3: 37.8 (#70), Mistral Small 3.1: 33.2 (#99)
| Benchmark | Kimi K3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | — | 1136 |
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), Mistral Small 3.1: 41.2 (#209)
| Benchmark | Kimi K3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1466 | 1255 |
| LMArena Chinese | 1529 | 1253 |
| LMArena French | 1491 | 1273 |
| LMArena German | 1488 | 1266 |
| LMArena Japanese | 1487 | 1208 |
| LMArena Korean | 1458 | 1206 |
| LMArena Russian | 1482 | 1263 |
| LMArena Spanish | 1472 | 1283 |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), Mistral Small 3.1: 63.6 (#230)
| Benchmark | Kimi K3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1483 | 1264 |
| IFEval | — | 75% |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), Mistral Small 3.1: 39.5 (#178)
| Benchmark | Kimi K3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1494 | 1299 |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Mistral Small 3.1: 37.0 (#259)
| Benchmark | Kimi K3 | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1476 | 1277 |
| LMArena Creative Writing | 1454 | 1253 |
| EQ-Bench Creative Writing | 2082 | 761 |
| LMArena Multi-Turn | 1488 | 1270 |
| WildBench | — | 78.8% |
| EQ-Bench 4 | 1339 | — |
Frequently asked questions
Is Kimi K3 better than Mistral Small 3.1?
Kimi K3 is the stronger model overall, scoring 59.5 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 15× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Kimi K3 or Mistral Small 3.1?
Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; Kimi K3 lists at $3 and $15.
Is Kimi K3 or Mistral Small 3.1 better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 38.3 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 128K.
How many benchmarks do Kimi K3 and Mistral Small 3.1 share?
22 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Mistral Small 3.1 has 28.