Model comparison
Codestral vs Kimi K3
Kimi K3 is the stronger model overall, scoring 59.5 to 30.6 on the Noometry Index. Codestral costs 13× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and Kimi K3 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 19.8.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 256K.
- Kimi K3 has downloadable open weights; the other is API-only.
Side by side
| Codestral | Kimi K3 | |
|---|---|---|
| Provider | Mistral AI | Moonshot AI |
| Noometry Index | 30.6 | 59.5 |
| Released | 2024-05-29 | 2026-07-16 |
| Weights | Proprietary | Open |
| Context window | 256K | 1.05M |
| Max output | 8K | 1.05M |
| Input $ / M tokens | $0.30 | $3 |
| Output $ / M tokens | $0.90 | $15 |
| Results tracked | 7 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Codestral: 27.3 (#321), Kimi K3: 61.0 (#10)
| Benchmark | Codestral | Kimi K3 |
|---|---|---|
| ALE-Bench | 137.78 | 1,524 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1654 |
| FrontierSWE | — | 25.9% |
| SciCode | — | 59.5% |
| WeirdML | — | 82.6% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1508 |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, Kimi K3: 41.8 (#20)
| Benchmark | Codestral | Kimi K3 |
|---|---|---|
| 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
Codestral: 19.8 (#251), Kimi K3: 63.0 (#17)
| Benchmark | Codestral | Kimi K3 |
|---|---|---|
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | — | 60.7% |
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 93.6% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 23.4% |
| Chess Puzzles | — | 39% |
| LMArena Hard Prompts | — | 1496 |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 91.2% |
| LMCA | — | 52.7% |
| Surface Evolver Bench | — | 95% |
| Epoch Capabilities Index | — | 157.45 |
| ForecastBench | — | 61.1 |
Math Not comparable
Codestral: —, Kimi K3: 74.2 (#16)
| Benchmark | Codestral | Kimi K3 |
|---|---|---|
| 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 |
Knowledge Not comparable
Codestral: —, Kimi K3: 63.2 (#21)
| Benchmark | Codestral | Kimi K3 |
|---|---|---|
| GPQA Diamond | — | 93.1% |
| SimpleQA Verified | — | 50.6% |
| LMArena Expert | — | 1521 |
Multimodal Not comparable
Codestral: —, Kimi K3: 37.8 (#70)
| Benchmark | Codestral | Kimi K3 |
|---|---|---|
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |
Multilingual Not comparable
Codestral: —, Kimi K3: 56.3 (#21)
| Benchmark | Codestral | Kimi K3 |
|---|---|---|
| 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
Codestral: —, Kimi K3: 77.7 (#14)
| Benchmark | Codestral | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | — | 1483 |
Long Context Not comparable
Codestral: —, Kimi K3: 45.8 (#29)
| Benchmark | Codestral | Kimi K3 |
|---|---|---|
| LMArena Longer Query | — | 1494 |
Writing & Preference Not comparable
Codestral: —, Kimi K3: 76.6 (#4)
| Benchmark | Codestral | Kimi K3 |
|---|---|---|
| LMArena Text | — | 1476 |
| LMArena Creative Writing | — | 1454 |
| EQ-Bench Creative Writing | — | 2082 |
| EQ-Bench 4 | — | 1339 |
| LMArena Multi-Turn | — | 1488 |
Frequently asked questions
Is Codestral better than Kimi K3?
Kimi K3 is the stronger model overall, scoring 59.5 to 30.6 on the Noometry Index. Codestral costs 13× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Codestral or Kimi K3?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Kimi K3 lists at $3 and $15.
Is Codestral or Kimi K3 better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 256K.
How many benchmarks do Codestral and Kimi K3 share?
1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and Kimi K3 has 53.