Model comparison
Kimi K3 vs Mistral Nemo
Kimi K3 is the stronger model overall, scoring 59.5 to 26.4 on the Noometry Index. Mistral Nemo costs 40× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Mistral AISummary
- They share 4 benchmarks with published results for both. Kimi K3 scores higher in 5 categories and Mistral Nemo in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K3 leads 63.2 to 12.3.
- The biggest single-benchmark swing is GPQA Diamond: 93.1% for Kimi K3 and 29.9% for Mistral Nemo.
- Mistral Nemo is cheaper at $0.15 / $0.15 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 Nemo | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 59.5 | 26.4 |
| Released | 2026-07-16 | 2024-07-01 |
| Weights | Open | Open |
| Context window | 1.05M | 128K |
| Max output | 1.05M | 128K |
| Input $ / M tokens | $3 | $0.15 |
| Output $ / M tokens | $15 | $0.15 |
| Results tracked | 53 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Kimi K3: 61.0 (#10), Mistral Nemo: —
| Benchmark | Kimi K3 | Mistral Nemo |
|---|---|---|
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| SciCode | 59.5% | — |
| WeirdML | 82.6% | — |
| LMArena Coding | 1508 | — |
| ALE-Bench | 1,524 | — |
Agentic & Tool Use Kimi K3 leads
Kimi K3: 41.8 (#20), Mistral Nemo: 23.5 (#125)
| Benchmark | Kimi K3 | Mistral Nemo |
|---|---|---|
| APEX-Agents | 50.6% | — |
| Berkeley Function Calling Leaderboard | — | 27.6% |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 32% | — |
| BALROG | — | 17.6% |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), Mistral Nemo: 20.7 (#232)
| Benchmark | Kimi K3 | Mistral Nemo |
|---|---|---|
| DTBench | 91.2% | 48.6% |
| Epoch Capabilities Index | 157.45 | 118.68 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 23.4% | — |
| Chess Puzzles | 39% | — |
| LMArena Hard Prompts | 1496 | — |
| Mystery Game Puzzles | 26% | — |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
| ForecastBench | 61.1 | — |
| PIQA | — | 83.5% |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Mistral Nemo: 25.5 (#268)
| Benchmark | Kimi K3 | Mistral Nemo |
|---|---|---|
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 97.2% | — |
| ProofBench | 87% | — |
| LMArena Math | 1491 | — |
| MATH Level 5 | — | 10.8% |
| GSM8K | — | 84.2% |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), Mistral Nemo: 12.3 (#298)
| Benchmark | Kimi K3 | Mistral Nemo |
|---|---|---|
| GPQA Diamond | 93.1% | 29.9% |
| SimpleQA Verified | 50.6% | — |
| LMArena Expert | 1521 | — |
| BoolQ | — | 82.5% |
Multimodal Not comparable
Kimi K3: 37.8 (#70), Mistral Nemo: —
| Benchmark | Kimi K3 | Mistral Nemo |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Not comparable
Kimi K3: 56.3 (#21), Mistral Nemo: —
| Benchmark | Kimi K3 | Mistral Nemo |
|---|---|---|
| LMArena Non-English | 1466 | — |
| LMArena Chinese | 1529 | — |
| LMArena French | 1491 | — |
| LMArena German | 1488 | — |
| LMArena Japanese | 1487 | — |
| LMArena Korean | 1458 | — |
| LMArena Russian | 1482 | — |
| LMArena Spanish | 1472 | — |
Instruction Following Not comparable
Kimi K3: 77.7 (#14), Mistral Nemo: —
| Benchmark | Kimi K3 | Mistral Nemo |
|---|---|---|
| LMArena Instruction Following | 1483 | — |
Long Context Not comparable
Kimi K3: 45.8 (#29), Mistral Nemo: —
| Benchmark | Kimi K3 | Mistral Nemo |
|---|---|---|
| LMArena Longer Query | 1494 | — |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Mistral Nemo: 28.5 (#296)
| Benchmark | Kimi K3 | Mistral Nemo |
|---|---|---|
| EQ-Bench Creative Writing | 2082 | 881 |
| LMArena Text | 1476 | — |
| LMArena Creative Writing | 1454 | — |
| EQ-Bench 4 | 1339 | — |
| LMArena Multi-Turn | 1488 | — |
Frequently asked questions
Is Kimi K3 better than Mistral Nemo?
Kimi K3 is the stronger model overall, scoring 59.5 to 26.4 on the Noometry Index. Mistral Nemo costs 40× 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 Nemo?
Mistral Nemo is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Kimi K3 lists at $3 and $15.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 128K.
How many benchmarks do Kimi K3 and Mistral Nemo share?
4 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Mistral Nemo has 10.