Skip to content
Model Pareto

Hy4 preview

Tencent HunyuanOpen weightshuggingface.co ↗
Compare with nearest rivalsCompare with…
Input
$0.834/M tok
Output
$2.501/M tok
Blended
$1.251/M tok · 3:1
Speed
~78tok/sest.
Context
1Mtokens

Open weights (Apache 2.0), 770B total / 49B active MoE. Price per https://www.tencent.com/tencent-releases-and-open-sources-tencent-hy4-preview/ (Tencent Cloud TokenHub). Not on AA or LMArena yet; its GDPval-AA V2 and AutomationBench v1.0.6 figures use a different version than our AA benchmarks, so they are left out.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.

Hardware
16× H200 141GB
FP8 weights
Throughput
~25,961 tok/s
many requests batched
Price
$0.33–2.71 /M tok
busy → light use
On your own machine
Mac Studio M5 Ultra 512GB (int4, ~34 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (770B params, 49B active per token) + 40% KV-cache headroom ≈ 1078 GB
  • 16× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~25,961 output tok/s aggregate at batch 1098 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~129,766 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench VerifiedEstimated
~#3 of 14 (estimated)~85.0%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. ~#3Hy4 previewEstimated85.0%
  4. #3Gemini 3.1 Pro80.6%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Estimated
~#15 of 84 (estimated)~26.3%
  1. #1Claude Sonnet 5.563.6%
  2. #2Claude Opus 5.559.6%
  3. #14DeepSeek V4.1 Flash26.8%
  4. ~#15Hy4 previewEstimated26.3%
  5. #15Grok 4.725.8%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#4 of 20 (estimated)~89.9%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #3Qwen3.8 27B90.3%
  4. ~#4Hy4 previewEstimated89.9%
  5. #4Nemotron 3 Ultra89.0%
No published score — estimated from related benchmarks
SciCodeEstimated
~#16 of 96 (estimated)~55.6%
  1. #1Claude Opus 5.566.9%
  2. #2Claude Fable 5.163.1%
  3. #15GPT-5.555.8%
  4. ~#16Hy4 previewEstimated55.6%
  5. #16GPT-5.6 Terra55.0%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#9 of 15 (estimated)~52.9
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #8GLM-5.353.6
  4. ~#9Hy4 previewEstimated52.9
  5. #9Kimi K351.9
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#2 of 25 (estimated)~96.6%
  1. #1Inkling97.1%
  2. ~#2Hy4 previewEstimated96.6%
  3. #2Muse Glimmer94.7%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#23 of 75 (estimated)~37.6
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556.0
  3. #22Claude Sonnet 538.2
  4. ~#23Hy4 previewEstimated37.6
  5. #23GPT-6 Luna37.3
No published score — estimated from related benchmarks