Skip to content

Hy4 preview

Tencent·Released Aug 28, 2026Open weights

Updated Oct 8, 11:55 PM ET

Overall score
59.6
Not ranked yet: results from only one evaluator so far
Evidence
13 results
39% of scored kinds covered
Context window
1M tokens
From OpenRouter
API price, USD per 1M tokens
$0.83 / $2.50
Input / output · cached input $0.042

The score is on the board's scale (reference average 50, about 15 points per standard deviation), not a percentage.

By domain

Each domain is scored on the same scale as the overall score. Coverage is the share of the domain's kinds of evaluation with a result; it says how much evidence there is, not how good the model is.

Coding
60.2
5 results · 56% coverage
Research and reasoning
58.9
2 results · 25% coverage
Professional work
59.4
6 results · 67% coverage
Knowledge and accuracy
59.6
Not tested yet: shows the overall level
Human preference
59.6
Not tested yet: shows the overall level

Every result behind the score

The result as the evaluator publishes it, and the reading it gives on the board's scale. A hard evaluation can give a high reading for a modest result; results near 95% or 5% only say "at least" or "at most".

Coding

5 results · 60.2

Research and reasoning

2 results · 58.9

Professional work

6 results · 59.4

Shown, not scored

Composite indices, saturated or older evaluations, evaluations still being checked, and vision, writing and multilingual results. They do not move the score.

  • IOIVals AI · CodingReference only59.3%
  • SRE BenchVals AI · CodingWatching2.3%
  • BioMysteryBenchVals AI · Research and reasoningWatching69.3%
  • LegalBenchVals AI · Professional workReference only83.8%
  • MedScribeVals AI · Professional workWatching83.6%
  • Vals IndexVals AI · Composite indicesReference only49.9%
  • Arena WebDevLMArena · Writing and designReference only1,631.7

No result yet

Scored evaluations this model has not taken. A missing result neither adds nor subtracts.

  • Terminal-Bench 4.0 (AA run) · Artificial Analysis
  • LiveBench Coding · LiveBench
  • Vibe Code Bench 1–100 · Vals AI
  • APEX-SWE · Mercor
  • SciCode · Artificial Analysis
  • FrontierMath Tiers 1–3 · Epoch AI
  • FrontierMath Tier 4 · Epoch AI
  • LiveBench Reasoning · LiveBench
  • Chess Puzzles · Epoch AI
  • Mystery Game Puzzles · Epoch AI
  • MysteryMechanism · Vals AI
  • Humanity's Last Exam (AA run) · Artificial Analysis
  • APEX-Agents · Mercor
  • LiveBench Data Analysis · LiveBench
  • τ²-Bench Telecom (AA run) · Artificial Analysis
  • τ-Bench Banking (AA run) · Artificial Analysis
  • SimpleQA Verified · Epoch AI
  • LiveBench Language · LiveBench
  • LiveBench Instruction Following · LiveBench
  • BullshitBench · BullshitBench
  • AA-LCR · Artificial Analysis
  • IFBench (AA run) · Artificial Analysis
  • Arena Text · LMArena
How readings and scores are computed