Model comparison
Kimi K2.7 Code vs Mistral Medium
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 36.3 on the Noometry Index.
Last verified . 8 shared benchmarks.
Mistral AISummary
- They share 8 benchmarks with published results for both. Kimi K2.7 Code scores higher in 4 categories and Mistral Medium in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.7 Code leads 53.5 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Kimi K2.7 Code and 32.2% for Mistral Medium.
- Kimi K2.7 Code is cheaper at $0.95 / $4 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
Side by side
| Kimi K2.7 Code | Mistral Medium | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 43.3 | 36.3 |
| Released | 2026-06-12 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 262K |
| Input $ / M tokens | $0.95 | $1.50 |
| Output $ / M tokens | $4 | $7.50 |
| Results tracked | 19 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.7 Code leads
Kimi K2.7 Code: 42.9 (#95), Mistral Medium: 34.2 (#243)
| Benchmark | Kimi K2.7 Code | Mistral Medium |
|---|---|---|
| FrontierCode | 30.1% | 8% |
| SciCode | 47.5% | 40.2% |
| WeirdML | 54.1% | 43.7% |
| ALE-Bench | 886.23 | 763.98 |
| DeepSWE | 30.5% | — |
| LMArena WebDev | 1473 | — |
| LMArena Coding | — | 1434 |
Agentic & Tool Use Mistral Medium leads
Kimi K2.7 Code: 24.0 (#122), Mistral Medium: 28.3 (#90)
| Benchmark | Kimi K2.7 Code | Mistral Medium |
|---|---|---|
| APEX-Agents | 37.6% | — |
| Berkeley Function Calling Leaderboard | — | 37.7% |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |
Reasoning Kimi K2.7 Code leads
Kimi K2.7 Code: 39.0 (#61), Mistral Medium: 24.0 (#167)
| Benchmark | Kimi K2.7 Code | Mistral Medium |
|---|---|---|
| CritPt | 10% | 0% |
| Surface Evolver Bench | 48.8% | 26.9% |
| SimpleBench | 57.9% | — |
| Kagi LLM Benchmark | — | 50% |
| Chess Puzzles | 21% | — |
| LMArena Hard Prompts | — | 1426 |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Epoch Capabilities Index | 149.97 | — |
Math Kimi K2.7 Code leads
Kimi K2.7 Code: 52.9 (#48), Mistral Medium: 28.1 (#245)
| Benchmark | Kimi K2.7 Code | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 32.2% |
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| ProofBench | — | 9% |
| LMArena Math | — | 1408 |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Kimi K2.7 Code leads
Kimi K2.7 Code: 53.5 (#57), Mistral Medium: 25.0 (#265)
| Benchmark | Kimi K2.7 Code | Mistral Medium |
|---|---|---|
| GPQA Diamond | 87.9% | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 36.5% | — |
| Vectara Hallucination Rate | — | 22.7% |
| LMArena Expert | — | 1408 |
Multimodal Not comparable
Kimi K2.7 Code: —, Mistral Medium: 35.3 (#88)
| Benchmark | Kimi K2.7 Code | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Not comparable
Kimi K2.7 Code: —, Mistral Medium: 52.1 (#91)
| Benchmark | Kimi K2.7 Code | Mistral Medium |
|---|---|---|
| LMArena Non-English | — | 1408 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1459 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1380 |
| LMArena Russian | — | 1411 |
| LMArena Spanish | — | 1433 |
Instruction Following Not comparable
Kimi K2.7 Code: —, Mistral Medium: 73.7 (#116)
| Benchmark | Kimi K2.7 Code | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | — | 1398 |
Long Context Not comparable
Kimi K2.7 Code: —, Mistral Medium: 42.9 (#114)
| Benchmark | Kimi K2.7 Code | Mistral Medium |
|---|---|---|
| LMArena Longer Query | — | 1406 |
Writing & Preference Not comparable
Kimi K2.7 Code: —, Mistral Medium: 60.0 (#103)
| Benchmark | Kimi K2.7 Code | Mistral Medium |
|---|---|---|
| LMArena Text | — | 1424 |
| LMArena Creative Writing | — | 1391 |
| Short-Story Creative Writing | — | 77.3% |
| LMArena Multi-Turn | — | 1418 |
Frequently asked questions
Is Kimi K2.7 Code better than Mistral Medium?
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 36.3 on the Noometry Index.
Which is cheaper, Kimi K2.7 Code or Mistral Medium?
Kimi K2.7 Code is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Kimi K2.7 Code or Mistral Medium better for coding?
Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Kimi K2.7 Code and Mistral Medium share?
8 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Mistral Medium has 36.