Model comparison
Claude Opus 5.5 vs Kimi K3
Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 59.5 on the Noometry Index.
Last verified . 39 shared benchmarks.
Summary
- They share 39 benchmarks with published results for both. Claude Opus 5.5 scores higher in 10 categories and Kimi K3 in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where Claude Opus 5.5 leads 57.8 to 37.8.
- The biggest single-benchmark swing is FrontierMath Tier 4: 95% for Claude Opus 5.5 and 39% for Kimi K3.
- Kimi K3 is cheaper at $3 / $15 per million input/output tokens, against $4 / $20 for Claude Opus 5.5.
- Kimi K3 accepts more context: 1.05M tokens versus 1M.
- Kimi K3 has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 5.5 | Kimi K3 | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 68.6 | 59.5 |
| Released | 2026-09-22 | 2026-07-16 |
| Weights | Proprietary | Open |
| Context window | 1M | 1.05M |
| Max output | 128K | 1.05M |
| Input $ / M tokens | $4 | $3 |
| Output $ / M tokens | $20 | $15 |
| Results tracked | 44 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5.5 leads
Claude Opus 5.5: 71.9 (#3), Kimi K3: 61.0 (#10)
| Benchmark | Claude Opus 5.5 | Kimi K3 |
|---|---|---|
| FrontierCode | 54.6% | 44.2% |
| LMArena WebDev | 1813 | 1654 |
| FrontierSWE | 62.3% | 25.9% |
| SciCode | 66.9% | 59.5% |
| LMArena Coding | 1547 | 1508 |
| ALE-Bench | 2,147 | 1,524 |
| DeepSWE | — | 68.5% |
| CursorBench | 57.8% | — |
| WeirdML | — | 82.6% |
| MirrorCode | 77.4% | — |
Agentic & Tool Use Claude Opus 5.5 leads
Claude Opus 5.5: 45.3 (#15), Kimi K3: 41.8 (#20)
| Benchmark | Claude Opus 5.5 | Kimi K3 |
|---|---|---|
| APEX-Agents | 73.5% | 50.6% |
| GDP.pdf | 30.6% | 19% |
| Vending-Bench 2 | 9,235 | 5,165 |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 32% |
| GBAEval | — | 48.3% |
Reasoning Claude Opus 5.5 leads
Claude Opus 5.5: 80.2 (#3), Kimi K3: 63.0 (#17)
| Benchmark | Claude Opus 5.5 | Kimi K3 |
|---|---|---|
| ARC-AGI-2 | 93.3% | 60.4% |
| NYT Connections (extended) | 88.5% | 93.6% |
| ARC-AGI-1 | 98.5% | 94.5% |
| CritPt | 31.7% | 23.4% |
| LMArena Hard Prompts | 1535 | 1496 |
| Mystery Game Puzzles | 71% | 26% |
| DTBench | 98.9% | 91.2% |
| LMCA | 68.2% | 52.7% |
| Epoch Capabilities Index | 167.33 | 157.45 |
| SimpleBench | — | 60.7% |
| Chess Puzzles | — | 39% |
| EBR-Bench | 71.4% | — |
| Surface Evolver Bench | — | 95% |
| ForecastBench | — | 61.1 |
Math Claude Opus 5.5 leads
Claude Opus 5.5: 91.8 (#3), Kimi K3: 74.2 (#16)
| Benchmark | Claude Opus 5.5 | Kimi K3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 91.2% | 72.2% |
| FrontierMath Tier 4 | 95% | 39% |
| OTIS Mock AIME 2024-2025 | 100% | 97.2% |
| ProofBench | 100% | 87% |
| LMArena Math | 1506 | 1491 |
| MathArena Final-Answer Competitions | — | 87.8% |
| FrontierMath Erdős | 2.9% | — |
Knowledge Claude Opus 5.5 leads
Claude Opus 5.5: 66.4 (#10), Kimi K3: 63.2 (#21)
| Benchmark | Claude Opus 5.5 | Kimi K3 |
|---|---|---|
| GPQA Diamond | 90.6% | 93.1% |
| SimpleQA Verified | 72.2% | 50.6% |
| LMArena Expert | 1547 | 1521 |
Multimodal Claude Opus 5.5 leads
Claude Opus 5.5: 57.8 (#1), Kimi K3: 37.8 (#70)
| Benchmark | Claude Opus 5.5 | Kimi K3 |
|---|---|---|
| Blueprint-Bench 2 | 51.2% | 29.5% |
| Furniture Assembly | 83.3% | 34.2% |
| LMArena Vision | 1321 | — |
Multilingual Claude Opus 5.5 leads
Claude Opus 5.5: 59.1 (#2), Kimi K3: 56.3 (#21)
| Benchmark | Claude Opus 5.5 | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1507 | 1466 |
| LMArena Chinese | 1588 | 1529 |
| LMArena French | 1514 | 1491 |
| LMArena Russian | 1520 | 1482 |
| LMArena Spanish | 1507 | 1472 |
| LMArena German | — | 1488 |
| LMArena Japanese | — | 1487 |
| LMArena Korean | — | 1458 |
Instruction Following Claude Opus 5.5 leads
Claude Opus 5.5: 80.0 (#3), Kimi K3: 77.7 (#14)
| Benchmark | Claude Opus 5.5 | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1537 | 1483 |
Long Context Claude Opus 5.5 leads
Claude Opus 5.5: 47.1 (#19), Kimi K3: 45.8 (#29)
| Benchmark | Claude Opus 5.5 | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1532 | 1494 |
Writing & Preference Claude Opus 5.5 leads
Claude Opus 5.5: 78.2 (#3), Kimi K3: 76.6 (#4)
| Benchmark | Claude Opus 5.5 | Kimi K3 |
|---|---|---|
| LMArena Text | 1515 | 1476 |
| LMArena Creative Writing | 1533 | 1454 |
| EQ-Bench Creative Writing | 2050 | 2082 |
| LMArena Multi-Turn | 1499 | 1488 |
| EQ-Bench 4 | — | 1339 |
Frequently asked questions
Is Claude Opus 5.5 better than Kimi K3?
Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 59.5 on the Noometry Index.
Which is cheaper, Claude Opus 5.5 or Kimi K3?
Kimi K3 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; Claude Opus 5.5 lists at $4 and $20.
Is Claude Opus 5.5 or Kimi K3 better for coding?
Claude Opus 5.5 scores higher on coding benchmarks: 71.9 versus 61.0 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 1M.
How many benchmarks do Claude Opus 5.5 and Kimi K3 share?
39 benchmarks have published results for both models. Claude Opus 5.5 has 44 scored results on Noometry and Kimi K3 has 53.