Model comparison
Kimi K2.5 vs Mistral Large 4
Kimi K2.5 is the stronger model overall, scoring 48.1 to 43.1 on the Noometry Index.
Last verified . 15 shared benchmarks.
Mistral AISummary
- They share 15 benchmarks with published results for both. Kimi K2.5 scores higher in 8 categories and Mistral Large 4 in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 36.6.
- The biggest single-benchmark swing is NYT Connections (extended): 69.9% for Kimi K2.5 and 27.4% for Mistral Large 4.
- Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $0.68 / $2.09 for Mistral Large 4.
- Mistral Large 4 accepts more context: 1.05M tokens versus 262K.
- Kimi K2.5 has downloadable open weights; the other is API-only.
Side by side
| Kimi K2.5 | Mistral Large 4 | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 48.1 | 43.1 |
| Released | 2026-01-27 | 2026-10-06 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.05M |
| Max output | 262K | 262K |
| Input $ / M tokens | $0.45 | $0.68 |
| Output $ / M tokens | $2.25 | $2.09 |
| Results tracked | 51 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Kimi K2.5: 48.8 (#53), Mistral Large 4: 48.6 (#57)
| Benchmark | Kimi K2.5 | Mistral Large 4 |
|---|---|---|
| LMArena WebDev | 1437 | 1541 |
| LMArena Coding | 1474 | 1475 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 70.8% | — |
| SWE-bench Multilingual | 67.3% | — |
| SciCode | 49% | — |
| WeirdML | 45.6% | — |
| ALE-Bench | 821.65 | — |
Agentic & Tool Use Not comparable
Kimi K2.5: 34.2 (#48), Mistral Large 4: —
| Benchmark | Kimi K2.5 | Mistral Large 4 |
|---|---|---|
| Terminal-Bench | 43.2% | — |
| OSWorld | 63.3% | — |
| Vending-Bench 2 | 1,198 | — |
Reasoning Kimi K2.5 leads
Kimi K2.5: 31.2 (#80), Mistral Large 4: 22.5 (#192)
| Benchmark | Kimi K2.5 | Mistral Large 4 |
|---|---|---|
| NYT Connections (extended) | 69.9% | 27.4% |
| LMArena Hard Prompts | 1453 | 1444 |
| ARC-AGI-2 | 11.8% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 78.5% | — |
| ARC-AGI-1 | 65.3% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 3.4% | — |
| Thematic Generalization | 69.4% | — |
| Epoch Capabilities Index | 148.03 | — |
Math Kimi K2.5 leads
Kimi K2.5: 51.8 (#53), Mistral Large 4: 40.4 (#91)
| Benchmark | Kimi K2.5 | Mistral Large 4 |
|---|---|---|
| LMArena Math | 1470 | 1488 |
| MathArena Final-Answer Competitions | 62.3% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| FrontierMath (Feb 2025 set) | 27.9% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Kimi K2.5 leads
Kimi K2.5: 53.6 (#56), Mistral Large 4: 36.6 (#166)
| Benchmark | Kimi K2.5 | Mistral Large 4 |
|---|---|---|
| SimpleQA Verified | 34.3% | 20% |
| LMArena Expert | 1466 | 1447 |
| GPQA Diamond | 87.6% | — |
| Humanity's Last Exam | 24.4% | — |
| Vectara Hallucination Rate | 14.2% | — |
Multimodal Not comparable
Kimi K2.5: 41.1 (#39), Mistral Large 4: —
| Benchmark | Kimi K2.5 | Mistral Large 4 |
|---|---|---|
| LMArena Vision | 1269 | — |
| LMArena Document | 1430 | — |
Multilingual Kimi K2.5 leads
Kimi K2.5: 53.9 (#53), Mistral Large 4: 52.6 (#82)
| Benchmark | Kimi K2.5 | Mistral Large 4 |
|---|---|---|
| LMArena Non-English | 1433 | 1415 |
| LMArena Chinese | 1495 | 1491 |
| LMArena Russian | 1435 | 1414 |
| LMArena French | 1454 | — |
| LMArena German | 1441 | — |
| LMArena Japanese | 1421 | — |
| LMArena Korean | 1410 | — |
| LMArena Spanish | 1450 | — |
Instruction Following Too close to call
Kimi K2.5: 75.3 (#64), Mistral Large 4: 75.0 (#76)
| Benchmark | Kimi K2.5 | Mistral Large 4 |
|---|---|---|
| LMArena Instruction Following | 1431 | 1424 |
Long Context Kimi K2.5 leads
Kimi K2.5: 52.1 (#7), Mistral Large 4: 43.6 (#89)
| Benchmark | Kimi K2.5 | Mistral Large 4 |
|---|---|---|
| LMArena Longer Query | 1445 | 1429 |
| 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), Mistral Large 4: 60.4 (#97)
| Benchmark | Kimi K2.5 | Mistral Large 4 |
|---|---|---|
| LMArena Text | 1445 | 1427 |
| LMArena Creative Writing | 1423 | 1361 |
| LMArena Multi-Turn | 1444 | 1424 |
| EQ-Bench Creative Writing | 1579 | — |
Frequently asked questions
Is Kimi K2.5 better than Mistral Large 4?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 43.1 on the Noometry Index.
Which is cheaper, Kimi K2.5 or Mistral Large 4?
Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; Mistral Large 4 lists at $0.68 and $2.09.
Is Kimi K2.5 or Mistral Large 4 better for coding?
They score almost the same on coding (48.8 vs 48.6); test both on your own repository before choosing.
Which has the bigger context window?
Mistral Large 4 does, with 1.05M tokens against 262K.
How many benchmarks do Kimi K2.5 and Mistral Large 4 share?
15 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Mistral Large 4 has 15.