Model comparison
Kimi K2.5 vs Mixtral 8x7B
Kimi K2.5 is the stronger model overall, scoring 48.1 to 27.1 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AISummary
- They share 19 benchmarks with published results for both. Kimi K2.5 scores higher in 8 categories and Mixtral 8x7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 11.0.
- The biggest single-benchmark swing is GPQA Diamond: 87.6% for Kimi K2.5 and 30.6% for Mixtral 8x7B.
- Mixtral 8x7B is cheaper at $0.70 / $0.70 per million input/output tokens, against $0.45 / $2.25 for Kimi K2.5.
- Kimi K2.5 accepts more context: 262K tokens versus 32K.
Side by side
| Kimi K2.5 | Mixtral 8x7B | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 48.1 | 27.1 |
| Released | 2026-01-27 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 262K | 32K |
| Max output | 262K | 32K |
| Input $ / M tokens | $0.45 | $0.70 |
| Output $ / M tokens | $2.25 | $0.70 |
| Results tracked | 51 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Kimi K2.5: 48.8 (#53), Mixtral 8x7B: 32.8 (#269)
| Benchmark | Kimi K2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1474 | 1126 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 70.8% | — |
| LMArena WebDev | 1437 | — |
| SWE-bench Multilingual | 67.3% | — |
| SciCode | 49% | — |
| WeirdML | 45.6% | — |
| ALE-Bench | 821.65 | — |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |
Agentic & Tool Use Not comparable
Kimi K2.5: 34.2 (#48), Mixtral 8x7B: —
| Benchmark | Kimi K2.5 | Mixtral 8x7B |
|---|---|---|
| Terminal-Bench | 43.2% | — |
| OSWorld | 63.3% | — |
| Vending-Bench 2 | 1,198 | — |
Reasoning Kimi K2.5 leads
Kimi K2.5: 31.2 (#80), Mixtral 8x7B: 18.2 (#285)
| Benchmark | Kimi K2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1453 | 1115 |
| Epoch Capabilities Index | 148.03 | 118.47 |
| ARC-AGI-2 | 11.8% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 78.5% | — |
| NYT Connections (extended) | 69.9% | — |
| ARC-AGI-1 | 65.3% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 3.4% | — |
| Thematic Generalization | 69.4% | — |
| DTBench | — | 49.6% |
| Adversarial NLI | — | 55.2% |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |
Math Kimi K2.5 leads
Kimi K2.5: 51.8 (#53), Mixtral 8x7B: 18.8 (#289)
| Benchmark | Kimi K2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Math | 1470 | 1147 |
| MathArena Final-Answer Competitions | 62.3% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| Omni-MATH | — | 10.5% |
| MATH Level 5 | — | 10% |
| FrontierMath (Feb 2025 set) | 27.9% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
| GSM8K | — | 74.4% |
Knowledge Kimi K2.5 leads
Kimi K2.5: 53.6 (#56), Mixtral 8x7B: 11.0 (#301)
| Benchmark | Kimi K2.5 | Mixtral 8x7B |
|---|---|---|
| GPQA Diamond | 87.6% | 30.6% |
| LMArena Expert | 1466 | 1088 |
| Humanity's Last Exam | 24.4% | — |
| SimpleQA Verified | 34.3% | — |
| MMLU-Pro | — | 33.5% |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | — | 29.6% |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multimodal Not comparable
Kimi K2.5: 41.1 (#39), Mixtral 8x7B: —
| Benchmark | Kimi K2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Vision | 1269 | — |
| LMArena Document | 1430 | — |
Multilingual Kimi K2.5 leads
Kimi K2.5: 53.9 (#53), Mixtral 8x7B: 29.6 (#266)
| Benchmark | Kimi K2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1433 | 1077 |
| LMArena Chinese | 1495 | 1055 |
| LMArena French | 1454 | 1166 |
| LMArena German | 1441 | 1114 |
| LMArena Japanese | 1421 | 931 |
| LMArena Korean | 1410 | 968 |
| LMArena Russian | 1435 | 1090 |
| LMArena Spanish | 1450 | 1111 |
Instruction Following Kimi K2.5 leads
Kimi K2.5: 75.3 (#64), Mixtral 8x7B: 51.0 (#297)
| Benchmark | Kimi K2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 1431 | 1109 |
| IFEval | — | 57.5% |
Long Context Kimi K2.5 leads
Kimi K2.5: 52.1 (#7), Mixtral 8x7B: 33.4 (#260)
| Benchmark | Kimi K2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1445 | 1103 |
| Fiction.LiveBench | 86.1% | — |
| CL-bench | 19.3% | — |
| CL-bench Life | 13.2% | — |
Writing & Preference Kimi K2.5 leads
Kimi K2.5: 65.1 (#53), Mixtral 8x7B: 34.2 (#270)
| Benchmark | Kimi K2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1445 | 1132 |
| LMArena Creative Writing | 1423 | 1109 |
| LMArena Multi-Turn | 1444 | 1115 |
| EQ-Bench Creative Writing | 1579 | — |
| WildBench | — | 67.3% |
Frequently asked questions
Is Kimi K2.5 better than Mixtral 8x7B?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 27.1 on the Noometry Index.
Which is cheaper, Kimi K2.5 or Mixtral 8x7B?
Mixtral 8x7B is cheaper. It lists at $0.70 per million input tokens and $0.70 per million output tokens; Kimi K2.5 lists at $0.45 and $2.25.
Is Kimi K2.5 or Mixtral 8x7B better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.5 does, with 262K tokens against 32K.
How many benchmarks do Kimi K2.5 and Mixtral 8x7B share?
19 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Mixtral 8x7B has 38.