Model comparison
Kimi K3 vs Mixtral 8x22B
Kimi K3 is the stronger model overall, scoring 59.5 to 27.1 on the Noometry Index. Mixtral 8x22B costs 2.0× 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 Mixtral 8x22B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.2 to 22.9.
- The biggest single-benchmark swing is WeirdML: 82.6% for Kimi K3 and 3.2% for Mixtral 8x22B.
- Mixtral 8x22B is cheaper at $2 / $6 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 64K.
Side by side
| Kimi K3 | Mixtral 8x22B | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 59.5 | 27.1 |
| Released | 2026-07-16 | 2024-04-17 |
| Weights | Open | Open |
| Context window | 1.05M | 64K |
| Max output | 1.05M | 64K |
| Input $ / M tokens | $3 | $2 |
| Output $ / M tokens | $15 | $6 |
| Results tracked | 53 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), Mixtral 8x22B: 24.2 (#329)
| Benchmark | Kimi K3 | Mixtral 8x22B |
|---|---|---|
| WeirdML | 82.6% | 3.2% |
| LMArena Coding | 1508 | 1166 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| SciCode | 59.5% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 1,524 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Kimi K3 leads
Kimi K3: 41.8 (#20), Mixtral 8x22B: 23.1 (#127)
| Benchmark | Kimi K3 | Mixtral 8x22B |
|---|---|---|
| APEX-Agents | 50.6% | — |
| τ²-bench Banking | 37.1% | — |
| Cybench | — | 7.5% |
| PostTrainBench | 32% | — |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), Mixtral 8x22B: 19.9 (#248)
| Benchmark | Kimi K3 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1496 | 1150 |
| DTBench | 91.2% | 55.1% |
| Epoch Capabilities Index | 157.45 | 122.03 |
| ForecastBench | 61.1 | 56.3 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 23.4% | — |
| Chess Puzzles | 39% | — |
| Mystery Game Puzzles | 26% | — |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Mixtral 8x22B: 22.9 (#275)
| Benchmark | Kimi K3 | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1491 | 1184 |
| 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% | — |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), Mixtral 8x22B: 15.1 (#293)
| Benchmark | Kimi K3 | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 93.1% | 34.1% |
| LMArena Expert | 1521 | 1113 |
| SimpleQA Verified | 50.6% | — |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |
Multimodal Not comparable
Kimi K3: 37.8 (#70), Mixtral 8x22B: —
| Benchmark | Kimi K3 | Mixtral 8x22B |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), Mixtral 8x22B: 32.8 (#255)
| Benchmark | Kimi K3 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1466 | 1128 |
| LMArena Chinese | 1529 | 1116 |
| LMArena French | 1491 | 1166 |
| LMArena German | 1488 | 1141 |
| LMArena Japanese | 1487 | 1037 |
| LMArena Korean | 1458 | 1057 |
| LMArena Russian | 1482 | 1158 |
| LMArena Spanish | 1472 | 1151 |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), Mixtral 8x22B: 57.7 (#266)
| Benchmark | Kimi K3 | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1483 | 1147 |
| IFEval | — | 72.4% |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), Mixtral 8x22B: 34.7 (#247)
| Benchmark | Kimi K3 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1494 | 1144 |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Mixtral 8x22B: 36.9 (#262)
| Benchmark | Kimi K3 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1476 | 1162 |
| LMArena Creative Writing | 1454 | 1141 |
| LMArena Multi-Turn | 1488 | 1130 |
| EQ-Bench Creative Writing | 2082 | — |
| WildBench | — | 71.1% |
| EQ-Bench 4 | 1339 | — |
Frequently asked questions
Is Kimi K3 better than Mixtral 8x22B?
Kimi K3 is the stronger model overall, scoring 59.5 to 27.1 on the Noometry Index. Mixtral 8x22B costs 2.0× 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 Mixtral 8x22B?
Mixtral 8x22B is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Kimi K3 lists at $3 and $15.
Is Kimi K3 or Mixtral 8x22B better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 64K.
How many benchmarks do Kimi K3 and Mixtral 8x22B share?
22 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Mixtral 8x22B has 34.