#59Tencent· released 2026-07-06

Tencent: Hy3.

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...

View on OpenRouter ↗
Context
262K
Input $/1M
$0.13
Output $/1M
$0.53
Modality
text
Arena Elo
1542
LMArena — human blind votes
AA Index
60.0
Artificial Analysis composite
LiveBench
73.8
Contamination-resistant
GPQA
80.7%
Grad-level science reasoning
MMLU-Pro
82.9%
Broad knowledge
SWE-bench
62.1%
Real GitHub bugs (Verified)
Terminal-Bench
47.2%
Agentic shell tasks
ARC-AGI
20.6%
Abstract reasoning
Aider Polyglot
70.2%
Multi-language code editing
Speed
83 tok/s
Median output speed

Profile

Tencent: Hy3 is Tencent's entry at position #59 on the current aggregated leaderboard. Its strongest signals are graduate-level science reasoning, real-world software engineering, unattended agentic work. Every figure below is aggregated from the public sources listed on the homepage and refreshed on each pipeline run.

The score spread is comparatively complete for this model, but the standing advice still applies: treat gaps of a few points as ties and validate on your own workload before committing.

How this model's position is computed is documented in the methodology; what each benchmark actually measures is in the benchmark guide. See a figure that disagrees with its source? Report it — accepted corrections apply on the next refresh.

Nearby on the leaderboard