Model comparison
Kimi K3 vs Mistral 7B
Kimi K3 is the stronger model overall, scoring 59.5 to 23.0 on the Noometry Index. Mistral 7B costs 24× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. Kimi K3 scores higher in 8 categories and Mistral 7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.2 to 8.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 97.2% for Kimi K3 and 0.3% for Mistral 7B.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 8K.
Side by side
| Kimi K3 | Mistral 7B | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 59.5 | 23.0 |
| Released | 2026-07-16 | 2023-09-27 |
| Weights | Open | Open |
| Context window | 1.05M | 8K |
| Max output | 1.05M | 8K |
| Input $ / M tokens | $3 | $0.25 |
| Output $ / M tokens | $15 | $0.25 |
| Results tracked | 53 | 37 |
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 7B: 26.4 (#326)
| Benchmark | Kimi K3 | Mistral 7B |
|---|---|---|
| LMArena Coding | 1508 | 1082 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| SciCode | 59.5% | — |
| WeirdML | 82.6% | — |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| ALE-Bench | 1,524 | — |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Agentic & Tool Use Not comparable
Kimi K3: 41.8 (#20), Mistral 7B: —
| Benchmark | Kimi K3 | Mistral 7B |
|---|---|---|
| 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 7B: 13.1 (#336)
| Benchmark | Kimi K3 | Mistral 7B |
|---|---|---|
| Chess Puzzles | 39% | 0% |
| LMArena Hard Prompts | 1496 | 1067 |
| DTBench | 91.2% | 42.5% |
| Epoch Capabilities Index | 157.45 | 112.21 |
| 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% | — |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| ForecastBench | 61.1 | — |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Mistral 7B: 8.1 (#325)
| Benchmark | Kimi K3 | Mistral 7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 97.2% | 0.3% |
| LMArena Math | 1491 | 1085 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| ProofBench | 87% | — |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), Mistral 7B: 7.4 (#311)
| Benchmark | Kimi K3 | Mistral 7B |
|---|---|---|
| GPQA Diamond | 93.1% | 15.2% |
| LMArena Expert | 1521 | 1036 |
| SimpleQA Verified | 50.6% | — |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multimodal Not comparable
Kimi K3: 37.8 (#70), Mistral 7B: —
| Benchmark | Kimi K3 | Mistral 7B |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), Mistral 7B: 25.8 (#283)
| Benchmark | Kimi K3 | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1466 | 1012 |
| LMArena Chinese | 1529 | 1009 |
| LMArena French | 1491 | 1037 |
| LMArena German | 1488 | 987 |
| LMArena Japanese | 1487 | 878 |
| LMArena Russian | 1482 | 1018 |
| LMArena Spanish | 1472 | 1026 |
| LMArena Korean | 1458 | — |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), Mistral 7B: 54.2 (#280)
| Benchmark | Kimi K3 | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1483 | 1060 |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), Mistral 7B: 32.2 (#271)
| Benchmark | Kimi K3 | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1494 | 1060 |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Mistral 7B: 30.7 (#286)
| Benchmark | Kimi K3 | Mistral 7B |
|---|---|---|
| LMArena Text | 1476 | 1090 |
| LMArena Creative Writing | 1454 | 1068 |
| LMArena Multi-Turn | 1488 | 1062 |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |
Frequently asked questions
Is Kimi K3 better than Mistral 7B?
Kimi K3 is the stronger model overall, scoring 59.5 to 23.0 on the Noometry Index. Mistral 7B costs 24× 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 7B?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Kimi K3 lists at $3 and $15.
Is Kimi K3 or Mistral 7B better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 8K.
How many benchmarks do Kimi K3 and Mistral 7B share?
21 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Mistral 7B has 37.