Compare / head-to-head
Hy3 previewvs
Seed1.8
Hy3 preview leads 3 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
3 – 0
Hy3 preview leads
Cheaper per token
—
list price, input + output
Larger context
Tie
both 256K tokens
Providers
2 providers
Tencent Hunyuan · ByteDance Seed
Hy3 preview
Tencent Hunyuan · released 2026-04-23
text
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 15 · 3 core
Quality
Benchmark matrix
3 shared · 12 only Hy3 preview · 13 only Seed1.8| Benchmark | Hy3 preview | Seed1.8 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 3 | ||||
| SWE-bench Verified | 74.4% ↗ | 72.9% ↗ | +1.5 pt | Hy3 preview |
| GPQA-Diamond | 87.2% ↗ | 83.8% ↗ | +3.4 pt | Hy3 preview |
| WideSearch | 70.2% ↗ | 63.8% ↗ | +6.4 pt | Hy3 preview |
| Only Hy3 preview reports · 12 | ||||
| AdvancedIF (CIF&CC subsets) | 79.5% ↗ | not reported | — | — |
| BrowseComp | 67.1% ↗ | 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 | — | — |
| WildClawBench (text-only) | 45.3% ↗ | not reported | — | — |
| Only Seed1.8 reports · 13 | ||||
| MMLU-Pro | not reported | 84.9% ↗ | — | — |
| AIME-25 | not reported | 94.3% ↗ | — | — |
| ARC-AGI-1 | not reported | 67.9% ↗ | — | — |
| BFCL-v4 | not reported | 57.2% ↗ | — | — |
| BrowseComp-en | not reported | 67.6% ↗ | — | — |
| HLE (text-only, agentic search) | not reported | 40.9% ↗ | — | — |
| LiveCodeBench(v6) | not reported | 79.5% ↗ | — | — |
| MM-BrowseComp | not reported | 46.3% ↗ | — | — |
| Multi-SWE-Bench | not reported | 42% ↗ | — | — |
| MultiChallenge | not reported | 66.7% ↗ | — | — |
| OSWorld-Verified (XLANG) | not reported | 61.9% ↗ | — | — |
| Terminal Bench 2.0 | not reported | 45.2% ↗ | — | — |
| τ2-Bench | not reported | 72% ↗ | — | — |
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 Seed1.8 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 | Seed1.8 | Edge |
|---|---|---|---|
| Context window | 256K tokens | 256K tokens | Tie |
| Max output | — | 64K tokens | — |
| Input price / 1M | — | $0.25 ↗ | — |
| Output price / 1M | — | $2 ↗ | — |
| Cached input / 1M | — | $0.05 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $2.25 | — |
| Modalities | text | text · vision · video | Seed1.8 |
| Released | 2026-04-23 | 2025-12-18 | — |
| Cited benchmark scores | 15 | 16 | — |
Reliability
Provider status
Live from /statusMore matchups
Hy3 preview vs …
Models sharing the most benchmarksMore matchups
Seed1.8 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Hy3 preview and Seed1.8 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.