Compare / head-to-head
Hy3 previewvs
Kimi K2.5
Kimi K2.5 leads 2 of 3 shared benchmarks. Both offer a 256K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 2
Kimi K2.5 leads
Cheaper per token
—
list price, input + output
Larger context
Tie
both 256K tokens
Providers
2 providers
Tencent Hunyuan · Moonshot AI
Hy3 preview
Tencent Hunyuan · released 2026-04-23
text
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 15 · 3 core
Kimi K2.5
Moonshot AI · released 2026-01-27
textvisionvideo
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 26 · 14 core
Quality
Benchmark matrix
3 shared · 12 only Hy3 preview · 23 only Kimi K2.5| Benchmark | Hy3 preview | Kimi K2.5 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 3 | ||||
| SWE-bench Verified | 74.4% ↗ | 76.8% ↗ | -2.4 pt | Kimi K2.5 |
| BrowseComp | 67.1% ↗ | 60.6% ↗ | +6.5 pt | Hy3 preview |
| GPQA-Diamond | 87.2% ↗ | 87.6% ↗ | -0.4 pt | Kimi K2.5 |
| Only Hy3 preview reports · 12 | ||||
| AdvancedIF (CIF&CC subsets) | 79.5% ↗ | not reported | — | — |
| CHSBO 2025 (text-only, pass^3) | 87.8% ↗ | not reported | — | — |
| CL-bench | 22.8% ↗ | not reported | — | — |
| CL-bench Life | 15.7% ↗ | not reported | — | — |
| ClawEval (pass^3) | 55% ↗ | not reported | — | — |
| FrontierScience Olympiad | 70% ↗ | not reported | — | — |
| HLE (text-only) | 30% ↗ | not reported | — | — |
| IMO Answer Bench | 84.3% ↗ | not reported | — | — |
| LongBench v2 | 65.4% ↗ | not reported | — | — |
| Terminal-Bench 2.0 | 54.4% ↗ | not reported | — | — |
| WideSearch | 70.2% ↗ | not reported | — | — |
| WildClawBench (text-only) | 45.3% ↗ | not reported | — | — |
| Only Kimi K2.5 reports · 23 | ||||
| MMLU-Pro | not reported | 87.1% ↗ | — | — |
| AIME 2025 | not reported | 96.1% ↗ | — | — |
| LMArena Elo | not reported | 1450.1 ↗ | — | — |
| HLE-Full | not reported | 30.1% ↗ | — | — |
| HLE-Full (w/ tools) | not reported | 50.2% ↗ | — | — |
| HMMT 2025 (Feb) | not reported | 95.4% ↗ | — | — |
| IMO-AnswerBench | not reported | 81.8% ↗ | — | — |
| LiveCodeBench (v6) | not reported | 85% ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1252.2 ↗ | — | — |
| LMArena WebDev (LMArena) | not reported | 1435.8 ↗ | — | — |
| MMMU-Pro | not reported | 78.5% ↗ | — | — |
| OSWorld-Verified (XLANG) | not reported | 63.3% ↗ | — | — |
| SAGE (Vals AI) | not reported | 49.9% ↗ | — | — |
| SimpleBench (SimpleBench) | not reported | 46.8% ↗ | — | — |
| SimpleQA Verified | not reported | 34.3% ↗epoch run | — | — |
| SWE-Bench Multilingual | not reported | 73% ↗ | — | — |
| SWE-Bench Pro | not reported | 50.7% ↗ | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 73.8% ↗epoch run | — | — |
| Terminal Bench 2.0 | not reported | 50.8% ↗ | — | — |
| Toolathlon-Verified (HKUST) | not reported | 33% ↗ | — | — |
| Vending-Bench 2 (Andon Labs) | not reported | 1198.46 ↗ | — | — |
| VideoMMMU | not reported | 86.6% ↗ | — | — |
| WeirdML (Håvard Tveit Ihle) | not reported | 45.6% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Hy3 preview minus Kimi K2.5 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Hy3 preview | Kimi K2.5 | Edge |
|---|---|---|---|
| Context window | 256K tokens | 256K tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text | text · vision · video | Kimi K2.5 |
| Released | 2026-04-23 | 2026-01-27 | — |
| Cited benchmark scores | 15 | 26 | — |
Reliability
Provider status
Live from /statusMore matchups
Hy3 preview vs …
Models sharing the most benchmarksMore matchups
Kimi K2.5 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Hy3 preview and Kimi K2.5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.