Model comparison
Claude Haiku 5.5 vs Kimi K3
Kimi K3 is the stronger model overall, scoring 59.5 to 49.5 on the Noometry Index. Claude Haiku 5.5 costs 30× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 9 shared benchmarks.
Summary
- They share 9 benchmarks with published results for both. Claude Haiku 5.5 scores higher in 1 category and Kimi K3 in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 35.2.
- The biggest single-benchmark swing is NYT Connections (extended): 65.7% for Claude Haiku 5.5 and 93.6% for Kimi K3.
- Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $3 / $15 for Kimi K3.
- 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 Haiku 5.5 | Kimi K3 | |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Noometry Index | 49.5 | 59.5 |
| Released | 2026-10-07 | 2026-07-16 |
| Weights | Proprietary | Open |
| Context window | 1M | 1.05M |
| Max output | 128K | 1.05M |
| Input $ / M tokens | $0.10 | $3 |
| Output $ / M tokens | $0.50 | $15 |
| Results tracked | 9 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Claude Haiku 5.5: 49.2 (#50), Kimi K3: 61.0 (#10)
| Benchmark | Claude Haiku 5.5 | Kimi K3 |
|---|---|---|
| LMArena WebDev | 1587 | 1654 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| FrontierSWE | — | 25.9% |
| SciCode | — | 59.5% |
| WeirdML | — | 82.6% |
| LMArena Coding | — | 1508 |
| ALE-Bench | — | 1,524 |
Agentic & Tool Use Not comparable
Claude Haiku 5.5: —, Kimi K3: 41.8 (#20)
| Benchmark | Claude Haiku 5.5 | Kimi K3 |
|---|---|---|
| APEX-Agents | — | 50.6% |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 32% |
| GBAEval | — | 48.3% |
| GDP.pdf | — | 19% |
| Vending-Bench 2 | — | 5,165 |
Reasoning Kimi K3 leads
Claude Haiku 5.5: 35.2 (#69), Kimi K3: 63.0 (#17)
| Benchmark | Claude Haiku 5.5 | Kimi K3 |
|---|---|---|
| NYT Connections (extended) | 65.7% | 93.6% |
| Mystery Game Puzzles | 30% | 26% |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | — | 60.7% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 23.4% |
| Chess Puzzles | — | 39% |
| LMArena Hard Prompts | — | 1496 |
| DTBench | — | 91.2% |
| LMCA | — | 52.7% |
| Surface Evolver Bench | — | 95% |
| Epoch Capabilities Index | — | 157.45 |
| ForecastBench | — | 61.1 |
Math Too close to call
Claude Haiku 5.5: 73.6 (#18), Kimi K3: 74.2 (#16)
| Benchmark | Claude Haiku 5.5 | Kimi K3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 75.1% | 72.2% |
| FrontierMath Tier 4 | 46.3% | 39% |
| OTIS Mock AIME 2024-2025 | 98.9% | 97.2% |
| MathArena Final-Answer Competitions | — | 87.8% |
| ProofBench | — | 87% |
| LMArena Math | — | 1491 |
Knowledge Kimi K3 leads
Claude Haiku 5.5: 50.8 (#70), Kimi K3: 63.2 (#21)
| Benchmark | Claude Haiku 5.5 | Kimi K3 |
|---|---|---|
| GPQA Diamond | 89.6% | 93.1% |
| SimpleQA Verified | 23.8% | 50.6% |
| LMArena Expert | — | 1521 |
Multimodal Claude Haiku 5.5 leads
Claude Haiku 5.5: 43.7 (#21), Kimi K3: 37.8 (#70)
| Benchmark | Claude Haiku 5.5 | Kimi K3 |
|---|---|---|
| Furniture Assembly | 47.5% | 34.2% |
| Blueprint-Bench 2 | — | 29.5% |
Multilingual Not comparable
Claude Haiku 5.5: —, Kimi K3: 56.3 (#21)
| Benchmark | Claude Haiku 5.5 | Kimi K3 |
|---|---|---|
| LMArena Non-English | — | 1466 |
| LMArena Chinese | — | 1529 |
| LMArena French | — | 1491 |
| LMArena German | — | 1488 |
| LMArena Japanese | — | 1487 |
| LMArena Korean | — | 1458 |
| LMArena Russian | — | 1482 |
| LMArena Spanish | — | 1472 |
Instruction Following Not comparable
Claude Haiku 5.5: —, Kimi K3: 77.7 (#14)
| Benchmark | Claude Haiku 5.5 | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | — | 1483 |
Long Context Not comparable
Claude Haiku 5.5: —, Kimi K3: 45.8 (#29)
| Benchmark | Claude Haiku 5.5 | Kimi K3 |
|---|---|---|
| LMArena Longer Query | — | 1494 |
Writing & Preference Not comparable
Claude Haiku 5.5: —, Kimi K3: 76.6 (#4)
| Benchmark | Claude Haiku 5.5 | Kimi K3 |
|---|---|---|
| LMArena Text | — | 1476 |
| LMArena Creative Writing | — | 1454 |
| EQ-Bench Creative Writing | — | 2082 |
| EQ-Bench 4 | — | 1339 |
| LMArena Multi-Turn | — | 1488 |
Frequently asked questions
Is Claude Haiku 5.5 better than Kimi K3?
Kimi K3 is the stronger model overall, scoring 59.5 to 49.5 on the Noometry Index. Claude Haiku 5.5 costs 30× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Claude Haiku 5.5 or Kimi K3?
Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Kimi K3 lists at $3 and $15.
Is Claude Haiku 5.5 or Kimi K3 better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 49.2 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 Haiku 5.5 and Kimi K3 share?
9 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and Kimi K3 has 53.