Model comparison
Claude 3 Opus vs Kimi K2.5
Kimi K2.5 is the stronger model overall, scoring 48.1 to 29.5 on the Noometry Index.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Kimi K2.5 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.5 leads 51.8 to 14.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 92.2% for Kimi K2.5.
- Kimi K2.5 has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | Kimi K2.5 | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 29.5 | 48.1 |
| Released | 2024-02-29 | 2026-01-27 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.45 |
| Output $ / M tokens | — | $2.25 |
| Results tracked | 46 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Claude 3 Opus: 32.9 (#267), Kimi K2.5: 48.8 (#53)
| Benchmark | Claude 3 Opus | Kimi K2.5 |
|---|---|---|
| WeirdML | 19.2% | 45.6% |
| LMArena Coding | 1264 | 1474 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| LMArena WebDev | — | 1437 |
| SWE-bench Multilingual | — | 67.3% |
| SciCode | — | 49% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 821.65 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Kimi K2.5 leads
Claude 3 Opus: 24.6 (#116), Kimi K2.5: 34.2 (#48)
| Benchmark | Claude 3 Opus | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| Cybench | 10% | — |
| OSWorld | — | 63.3% |
| METR Time Horizons | 29.5% | — |
| Vending-Bench 2 | — | 1,198 |
Reasoning Kimi K2.5 leads
Claude 3 Opus: 14.6 (#324), Kimi K2.5: 31.2 (#80)
| Benchmark | Claude 3 Opus | Kimi K2.5 |
|---|---|---|
| SimpleBench | 23.5% | 46.8% |
| Chess Puzzles | 5% | 12% |
| EnigmaEval | 0.8% | 3.4% |
| LMArena Hard Prompts | 1245 | 1453 |
| Epoch Capabilities Index | 126.91 | 148.03 |
| ARC-AGI-2 | — | 11.8% |
| Kagi LLM Benchmark | — | 78.5% |
| NYT Connections (extended) | — | 69.9% |
| ARC-AGI-1 | — | 65.3% |
| CritPt | — | 3.1% |
| Thematic Generalization | — | 69.4% |
| LiveBench Reasoning | 40.6% | — |
| DTBench | 61.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LMCA | 17% | — |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Kimi K2.5 leads
Claude 3 Opus: 14.8 (#299), Kimi K2.5: 51.8 (#53)
| Benchmark | Claude 3 Opus | Kimi K2.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 92.2% |
| LMArena Math | 1273 | 1470 |
| MathArena Final-Answer Competitions | — | 62.3% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Kimi K2.5 leads
Claude 3 Opus: 24.5 (#267), Kimi K2.5: 53.6 (#56)
| Benchmark | Claude 3 Opus | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 47.2% | 87.6% |
| SimpleQA Verified | 12.6% | 34.3% |
| LMArena Expert | 1223 | 1466 |
| Humanity's Last Exam | — | 24.4% |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 14.2% |
| MMLU | 84.6% | — |
Multimodal Kimi K2.5 leads
Claude 3 Opus: 27.1 (#116), Kimi K2.5: 41.1 (#39)
| Benchmark | Claude 3 Opus | Kimi K2.5 |
|---|---|---|
| LMArena Vision | 1023 | 1269 |
| LMArena Document | — | 1430 |
Multilingual Kimi K2.5 leads
Claude 3 Opus: 41.4 (#207), Kimi K2.5: 53.9 (#53)
| Benchmark | Claude 3 Opus | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1258 | 1433 |
| LMArena Chinese | 1248 | 1495 |
| LMArena French | 1275 | 1454 |
| LMArena German | 1258 | 1441 |
| LMArena Japanese | 1204 | 1421 |
| LMArena Korean | 1187 | 1410 |
| LMArena Russian | 1280 | 1435 |
| LMArena Spanish | 1246 | 1450 |
Instruction Following Kimi K2.5 leads
Claude 3 Opus: 64.1 (#228), Kimi K2.5: 75.3 (#64)
| Benchmark | Claude 3 Opus | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1431 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Kimi K2.5 leads
Claude 3 Opus: 38.2 (#202), Kimi K2.5: 52.1 (#7)
| Benchmark | Claude 3 Opus | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1259 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference Kimi K2.5 leads
Claude 3 Opus: 47.2 (#213), Kimi K2.5: 65.1 (#53)
| Benchmark | Claude 3 Opus | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1262 | 1445 |
| LMArena Creative Writing | 1235 | 1423 |
| LMArena Multi-Turn | 1275 | 1444 |
| EQ-Bench Creative Writing | — | 1579 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Kimi K2.5?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Kimi K2.5 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Kimi K2.5 share?
26 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Kimi K2.5 has 51.