Model comparison
Hy3 vs Kimi K3
Kimi K3 is the stronger model overall, scoring 59.5 to 44.2 on the Noometry Index. Hy3 costs 42× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
TencentSummary
- They share 19 benchmarks with published results for both. Hy3 scores higher in 0 categories and Kimi K3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 26.1.
- The biggest single-benchmark swing is NYT Connections (extended): 41.2% for Hy3 and 93.6% for Kimi K3.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 262K.
Side by side
| Hy3 | Kimi K3 | |
|---|---|---|
| Provider | Tencent | Moonshot AI |
| Noometry Index | 44.2 | 59.5 |
| Released | 2026-07-06 | 2026-07-16 |
| Weights | Open | Open |
| Context window | 262K | 1.05M |
| Max output | 128K | 1.05M |
| Input $ / M tokens | $0.0825 | $3 |
| Output $ / M tokens | $0.33 | $15 |
| Results tracked | 19 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Hy3: 46.8 (#63), Kimi K3: 61.0 (#10)
| Benchmark | Hy3 | Kimi K3 |
|---|---|---|
| LMArena WebDev | 1508 | 1654 |
| LMArena Coding | 1464 | 1508 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| FrontierSWE | — | 25.9% |
| SciCode | — | 59.5% |
| WeirdML | — | 82.6% |
| ALE-Bench | — | 1,524 |
Agentic & Tool Use Not comparable
Hy3: —, Kimi K3: 41.8 (#20)
| Benchmark | Hy3 | 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
Hy3: 26.1 (#136), Kimi K3: 63.0 (#17)
| Benchmark | Hy3 | Kimi K3 |
|---|---|---|
| NYT Connections (extended) | 41.2% | 93.6% |
| LMArena Hard Prompts | 1447 | 1496 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | — | 60.7% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 23.4% |
| Chess Puzzles | — | 39% |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 91.2% |
| LMCA | — | 52.7% |
| Surface Evolver Bench | — | 95% |
| Epoch Capabilities Index | — | 157.45 |
| ForecastBench | — | 61.1 |
Math Kimi K3 leads
Hy3: 40.1 (#93), Kimi K3: 74.2 (#16)
| Benchmark | Hy3 | Kimi K3 |
|---|---|---|
| LMArena Math | 1475 | 1491 |
| FrontierMath (Tiers 1-3) | — | 72.2% |
| FrontierMath Tier 4 | — | 39% |
| MathArena Final-Answer Competitions | — | 87.8% |
| OTIS Mock AIME 2024-2025 | — | 97.2% |
| ProofBench | — | 87% |
Knowledge Kimi K3 leads
Hy3: 40.8 (#114), Kimi K3: 63.2 (#21)
| Benchmark | Hy3 | Kimi K3 |
|---|---|---|
| LMArena Expert | 1460 | 1521 |
| GPQA Diamond | — | 93.1% |
| SimpleQA Verified | — | 50.6% |
Multimodal Not comparable
Hy3: —, Kimi K3: 37.8 (#70)
| Benchmark | Hy3 | Kimi K3 |
|---|---|---|
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |
Multilingual Kimi K3 leads
Hy3: 53.5 (#65), Kimi K3: 56.3 (#21)
| Benchmark | Hy3 | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1426 | 1466 |
| LMArena Chinese | 1493 | 1529 |
| LMArena French | 1461 | 1491 |
| LMArena German | 1439 | 1488 |
| LMArena Japanese | 1392 | 1487 |
| LMArena Korean | 1395 | 1458 |
| LMArena Russian | 1432 | 1482 |
| LMArena Spanish | 1456 | 1472 |
Instruction Following Kimi K3 leads
Hy3: 75.1 (#70), Kimi K3: 77.7 (#14)
| Benchmark | Hy3 | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1426 | 1483 |
Long Context Kimi K3 leads
Hy3: 44.1 (#75), Kimi K3: 45.8 (#29)
| Benchmark | Hy3 | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1442 | 1494 |
Writing & Preference Kimi K3 leads
Hy3: 62.2 (#81), Kimi K3: 76.6 (#4)
| Benchmark | Hy3 | Kimi K3 |
|---|---|---|
| LMArena Text | 1439 | 1476 |
| LMArena Creative Writing | 1402 | 1454 |
| LMArena Multi-Turn | 1436 | 1488 |
| EQ-Bench Creative Writing | — | 2082 |
| EQ-Bench 4 | — | 1339 |
Frequently asked questions
Is Hy3 better than Kimi K3?
Kimi K3 is the stronger model overall, scoring 59.5 to 44.2 on the Noometry Index. Hy3 costs 42× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Hy3 or Kimi K3?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Kimi K3 lists at $3 and $15.
Is Hy3 or Kimi K3 better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 46.8 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 262K.
How many benchmarks do Hy3 and Kimi K3 share?
19 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Kimi K3 has 53.