Model comparison
Claude 3 Opus vs Kimi K2 (Jul 2025)
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 29.5 on the Noometry Index.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Kimi K2 (Jul 2025) in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 (Jul 2025) leads 42.7 to 14.8.
- The biggest single-benchmark swing is WeirdML: 19.2% for Claude 3 Opus and 42.8% for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 29.5 | 41.2 |
| Released | 2024-02-29 | 2025-07-12 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.57 |
| Output $ / M tokens | — | $2.30 |
| Results tracked | 46 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Claude 3 Opus: 32.9 (#267), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | Claude 3 Opus | Kimi K2 (Jul 2025) |
|---|---|---|
| WeirdML | 19.2% | 42.8% |
| LMArena Coding | 1264 | 1399 |
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| GSO | — | 4.9% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 597.5 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
Claude 3 Opus: 24.6 (#116), Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | Claude 3 Opus | Kimi K2 (Jul 2025) |
|---|---|---|
| METR Time Horizons | 29.5% | 59.2% |
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| Cybench | 10% | — |
Reasoning Kimi K2 (Jul 2025) leads
Claude 3 Opus: 14.6 (#324), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | Claude 3 Opus | Kimi K2 (Jul 2025) |
|---|---|---|
| SimpleBench | 23.5% | 26.3% |
| LMArena Hard Prompts | 1245 | 1384 |
| Epoch Capabilities Index | 126.91 | 146.01 |
| ForecastBench | 58.4 | 60.2 |
| Kagi LLM Benchmark | — | 64.4% |
| Chess Puzzles | 5% | — |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| DTBench | 61.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LMCA | 17% | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Kimi K2 (Jul 2025) leads
Claude 3 Opus: 14.8 (#299), Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | Claude 3 Opus | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1273 | 1397 |
| OTIS Mock AIME 2024-2025 | 4.7% | — |
| Omni-MATH | — | 65.4% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Kimi K2 (Jul 2025) leads
Claude 3 Opus: 24.5 (#267), Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | Claude 3 Opus | Kimi K2 (Jul 2025) |
|---|---|---|
| Confabulations | 22.7% | 20.4% |
| LMArena Expert | 1223 | 1365 |
| GPQA Diamond | 47.2% | — |
| SimpleQA Verified | 12.6% | — |
| MMLU-Pro | — | 81.9% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |
| MMLU | 84.6% | — |
Multimodal Not comparable
Claude 3 Opus: 27.1 (#116), Kimi K2 (Jul 2025): —
| Benchmark | Claude 3 Opus | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1023 | — |
Multilingual Kimi K2 (Jul 2025) leads
Claude 3 Opus: 41.4 (#207), Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | Claude 3 Opus | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1258 | 1372 |
| LMArena Chinese | 1248 | 1415 |
| LMArena French | 1275 | 1379 |
| LMArena German | 1258 | 1387 |
| LMArena Japanese | 1204 | 1349 |
| LMArena Korean | 1187 | 1325 |
| LMArena Russian | 1280 | 1385 |
| LMArena Spanish | 1246 | 1386 |
Instruction Following Kimi K2 (Jul 2025) leads
Claude 3 Opus: 64.1 (#228), Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | Claude 3 Opus | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1248 | 1348 |
| LiveBench Instruction Following | 63.9% | — |
| IFEval | — | 85% |
Long Context Kimi K2 (Jul 2025) leads
Claude 3 Opus: 38.2 (#202), Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | Claude 3 Opus | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Longer Query | 1259 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
Claude 3 Opus: 47.2 (#213), Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | Claude 3 Opus | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1262 | 1380 |
| LMArena Creative Writing | 1235 | 1350 |
| LMArena Multi-Turn | 1275 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| EQ-Bench Creative Writing | — | 1666 |
| WildBench | — | 86.2% |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Kimi K2 (Jul 2025) share?
23 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Kimi K2 (Jul 2025) has 42.