Model comparison
Claude 3.5 Sonnet vs Kimi K2.5 Instant
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 34.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 0 categories and Kimi K2.5 Instant in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.5 Instant leads 39.4 to 19.2.
- Kimi K2.5 Instant has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | Kimi K2.5 Instant | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 34.6 | 43.6 |
| Released | 2024-06-20 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 60 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 Instant leads
Claude 3.5 Sonnet: 39.0 (#165), Kimi K2.5 Instant: 42.6 (#97)
| Benchmark | Claude 3.5 Sonnet | Kimi K2.5 Instant |
|---|---|---|
| LMArena Coding | 1342 | 1484 |
| Aider Polyglot | 51.6% | — |
| LMArena WebDev | — | 1404 |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.3 (#67), Kimi K2.5 Instant: —
| Benchmark | Claude 3.5 Sonnet | Kimi K2.5 Instant |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Kimi K2.5 Instant leads
Claude 3.5 Sonnet: 23.1 (#183), Kimi K2.5 Instant: 29.7 (#90)
| Benchmark | Claude 3.5 Sonnet | Kimi K2.5 Instant |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1443 |
| SimpleBench | 41.4% | — |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| DTBench | 67.8% | — |
| LiveBench Data Analysis | 55% | — |
| Epoch Capabilities Index | 133.55 | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math Kimi K2.5 Instant leads
Claude 3.5 Sonnet: 19.2 (#288), Kimi K2.5 Instant: 39.4 (#105)
| Benchmark | Claude 3.5 Sonnet | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | 1307 | 1442 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Kimi K2.5 Instant leads
Claude 3.5 Sonnet: 28.6 (#245), Kimi K2.5 Instant: 40.2 (#123)
| Benchmark | Claude 3.5 Sonnet | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | 1265 | 1440 |
| GPQA Diamond | 55.3% | — |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Kimi K2.5 Instant leads
Claude 3.5 Sonnet: 26.5 (#120), Kimi K2.5 Instant: 40.2 (#50)
| Benchmark | Claude 3.5 Sonnet | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | 1125 | 1254 |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Kimi K2.5 Instant leads
Claude 3.5 Sonnet: 43.2 (#185), Kimi K2.5 Instant: 52.0 (#94)
| Benchmark | Claude 3.5 Sonnet | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | 1283 | 1406 |
| LMArena Chinese | 1272 | 1449 |
| LMArena French | 1305 | 1403 |
| LMArena German | 1297 | 1413 |
| LMArena Korean | 1200 | 1378 |
| LMArena Russian | 1306 | 1404 |
| LMArena Spanish | 1290 | 1447 |
| LMArena Japanese | 1234 | — |
Instruction Following Kimi K2.5 Instant leads
Claude 3.5 Sonnet: 68.8 (#182), Kimi K2.5 Instant: 75.3 (#65)
| Benchmark | Claude 3.5 Sonnet | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1297 | 1430 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Kimi K2.5 Instant leads
Claude 3.5 Sonnet: 39.9 (#167), Kimi K2.5 Instant: 43.9 (#83)
| Benchmark | Claude 3.5 Sonnet | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | 1311 | 1435 |
Writing & Preference Kimi K2.5 Instant leads
Claude 3.5 Sonnet: 52.9 (#164), Kimi K2.5 Instant: 60.6 (#95)
| Benchmark | Claude 3.5 Sonnet | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | 1298 | 1420 |
| LMArena Creative Writing | 1292 | 1381 |
| LMArena Multi-Turn | 1326 | 1427 |
| Short-Story Creative Writing | 80.3% | — |
| EQ-Bench Creative Writing | 1451 | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Kimi K2.5 Instant?
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Kimi K2.5 Instant better for coding?
Kimi K2.5 Instant scores higher on coding benchmarks: 42.6 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Kimi K2.5 Instant share?
17 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Kimi K2.5 Instant has 18.