Model comparison
Claude Opus 4.1 vs Kimi K3
Kimi K3 is the stronger model overall, scoring 59.5 to 41.0 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. Claude Opus 4.1 scores higher in 0 categories and Kimi K3 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.2 to 22.3.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 12.6% for Claude Opus 4.1 and 72.2% for Kimi K3.
- Kimi K3 is cheaper at $3 / $15 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- Kimi K3 accepts more context: 1.05M tokens versus 200K.
- Kimi K3 has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.1 | Kimi K3 | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 41.0 | 59.5 |
| Released | 2025-08-05 | 2026-07-16 |
| Weights | Proprietary | Open |
| Context window | 200K | 1.05M |
| Max output | 32K | 1.05M |
| Input $ / M tokens | $15 | $3 |
| Output $ / M tokens | $75 | $15 |
| Results tracked | 48 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Claude Opus 4.1: 44.4 (#73), Kimi K3: 61.0 (#10)
| Benchmark | Claude Opus 4.1 | Kimi K3 |
|---|---|---|
| LMArena WebDev | 1390 | 1654 |
| WeirdML | 45.9% | 82.6% |
| LMArena Coding | 1479 | 1508 |
| ALE-Bench | 674.77 | 1,524 |
| SWE-bench Verified | 73.3% | — |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| FrontierSWE | — | 25.9% |
| SciCode | — | 59.5% |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Kimi K3 leads
Claude Opus 4.1: 35.0 (#41), Kimi K3: 41.8 (#20)
| Benchmark | Claude Opus 4.1 | Kimi K3 |
|---|---|---|
| Terminal-Bench | 38% | — |
| APEX-Agents | — | 50.6% |
| GDPval | 43.6% | — |
| τ²-bench Banking | — | 37.1% |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| PostTrainBench | — | 32% |
| GBAEval | — | 48.3% |
| GDP.pdf | — | 19% |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
| Vending-Bench 2 | — | 5,165 |
Reasoning Kimi K3 leads
Claude Opus 4.1: 32.2 (#76), Kimi K3: 63.0 (#17)
| Benchmark | Claude Opus 4.1 | Kimi K3 |
|---|---|---|
| SimpleBench | 60% | 60.7% |
| Chess Puzzles | 7% | 39% |
| LMArena Hard Prompts | 1443 | 1496 |
| Mystery Game Puzzles | 21% | 26% |
| DTBench | 80% | 91.2% |
| LMCA | 37.1% | 52.7% |
| Epoch Capabilities Index | 144.12 | 157.45 |
| ForecastBench | 62 | 61.1 |
| ARC-AGI-2 | — | 60.4% |
| NYT Connections (extended) | — | 93.6% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 23.4% |
| EnigmaEval | 7.2% | — |
| EBR-Bench | 7.9% | — |
| Surface Evolver Bench | — | 95% |
Math Kimi K3 leads
Claude Opus 4.1: 22.3 (#277), Kimi K3: 74.2 (#16)
| Benchmark | Claude Opus 4.1 | Kimi K3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 12.6% | 72.2% |
| FrontierMath Tier 4 | 2.4% | 39% |
| OTIS Mock AIME 2024-2025 | 68.9% | 97.2% |
| LMArena Math | 1431 | 1491 |
| MathArena Final-Answer Competitions | — | 87.8% |
| ProofBench | — | 87% |
| FrontierMath (Feb 2025 set) | 7.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Kimi K3 leads
Claude Opus 4.1: 42.0 (#101), Kimi K3: 63.2 (#21)
| Benchmark | Claude Opus 4.1 | Kimi K3 |
|---|---|---|
| GPQA Diamond | 77.3% | 93.1% |
| LMArena Expert | 1439 | 1521 |
| Humanity's Last Exam | 11.5% | — |
| SimpleQA Verified | — | 50.6% |
| Confabulations | 17.1% | — |
| Vectara Hallucination Rate | 11.8% | — |
Multimodal Kimi K3 leads
Claude Opus 4.1: 26.8 (#119), Kimi K3: 37.8 (#70)
| Benchmark | Claude Opus 4.1 | Kimi K3 |
|---|---|---|
| VPCT | 35% | — |
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |
Multilingual Kimi K3 leads
Claude Opus 4.1: 52.0 (#95), Kimi K3: 56.3 (#21)
| Benchmark | Claude Opus 4.1 | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1405 | 1466 |
| LMArena Chinese | 1427 | 1529 |
| LMArena French | 1431 | 1491 |
| LMArena German | 1413 | 1488 |
| LMArena Japanese | 1378 | 1487 |
| LMArena Korean | 1380 | 1458 |
| LMArena Russian | 1422 | 1482 |
| LMArena Spanish | 1448 | 1472 |
Instruction Following Kimi K3 leads
Claude Opus 4.1: 75.6 (#58), Kimi K3: 77.7 (#14)
| Benchmark | Claude Opus 4.1 | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1435 | 1483 |
Long Context Kimi K3 leads
Claude Opus 4.1: 44.5 (#63), Kimi K3: 45.8 (#29)
| Benchmark | Claude Opus 4.1 | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1455 | 1494 |
Writing & Preference Kimi K3 leads
Claude Opus 4.1: 62.4 (#74), Kimi K3: 76.6 (#4)
| Benchmark | Claude Opus 4.1 | Kimi K3 |
|---|---|---|
| LMArena Text | 1419 | 1476 |
| LMArena Creative Writing | 1412 | 1454 |
| LMArena Multi-Turn | 1444 | 1488 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 2082 |
| EQ-Bench 4 | — | 1339 |
Frequently asked questions
Is Claude Opus 4.1 better than Kimi K3?
Kimi K3 is the stronger model overall, scoring 59.5 to 41.0 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 or Kimi K3?
Kimi K3 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or Kimi K3 better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 44.4 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 200K.
How many benchmarks do Claude Opus 4.1 and Kimi K3 share?
31 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Kimi K3 has 53.