TencentLanguage model

Hy3 preview

Hy3 preview has no overall index value yet because there are too few independent benchmark results.

PopularityRank 228 of 785

43out of 100+7 vs. last month

based on search, usage and attention

Summary

Hy3 preview was released as an open-weight preview for practical agent work. Tencent uses a Mixture-of-Experts model with 295 billion total parameters, 21 billion active per token, and a 262,144-token context. The model supports no_think for direct responses and high for harder reasoning tasks.

The weights run locally with vLLM or SGLang. Tencent Cloud has routed hy3-preview calls in its Token Plan to Hy3 since July 24, 2026. The published preview remains a distinct checkpoint for inspection and local use, while the API alias points to Hy3 there.

See for yourself: one prompt, one attempt

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Hy3 preview

Earlier tests

The response reached the token limit. No complete recording is available.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Oct 5, 2026 · 62 s · $0.0049

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Test details

Run date: Oct 5, 2026
API provider: openrouter
Requested API model: tencent/hy3-preview
Reasoning setting: high
Token limit including reasoning: 8,192 tokens
Output tokens: 8,192 tokens
Cost of the attempt: $0.0049
Response time: 62.3 s
API model reported in response: tencent/hy3-preview
Pinned endpoint: GMICloud | tencent/hy3-preview-20260421
Temperature: Provider default
Test protocol: community-visual-tests-v1
Technical checks: Failed

Earlier attempts (2)

Oct 2, 2026API request failedReasoning setting: high
Oct 1, 2026API request failedReasoning setting: high

Task origin: Simon Willison

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 35 published benchmark results

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

CritPt v2: Overall (Show measurement, test conditions, and source)

Source value: 4.57142857142857
Score: 4.57142857142857
Metric: pass@1 accuracy
Unit: %
Benchmark version: v2
Category: reasoning
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: disputed
Retrieved at: 2026-11-02
Methodology: Exact AA configuration: Hy3-preview (Reasoning) (release hy3-preview, row hy3-preview, UUID 8ca48626-ff5e-48b3-8401-38081376d706, reasoning=true, effort=not specified, suffix=Reasoning). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Source model ID: artificial-analysis/8ca48626-ff5e-48b3-8401-38081376d706/hy3-preview/hy3-preview. Source model name: Hy3-preview. Provider reported by source: Tencent. Model snapshot: Hy3-preview (Reasoning). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: reasoning enabled. Score display: 4.6%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-critpt-v2:v2:standalone:reasoning:effort=unspecified:suffix=Reasoning
Comparison methodology: Exact AA configuration: Hy3-preview (Reasoning) (release hy3-preview, row hy3-preview, UUID 8ca48626-ff5e-48b3-8401-38081376d706, reasoning=true, effort=not specified, suffix=Reasoning). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: reasoning enabled
Context: This AA source field contains the original CritPt score. The earlier CritPt v2 attribution was incorrect; the value and former label remain as disputed historical evidence.. The source dataset marks this result as disputed. It remains visible as documented evidence, but is not reliable comparative proof.

Source Artificial Analysis

CritPt v2: Overall (Show measurement, test conditions, and source)

Source value: 0.28571428571428603
Score: 0.28571428571428603
Metric: pass@1 accuracy
Unit: %
Benchmark version: v2
Category: reasoning
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: disputed
Retrieved at: 2026-11-02
Methodology: Exact AA configuration: Hy3-preview (Non-reasoning) (release hy3-preview, row hy3-non-reasoning, UUID b58b8272-cd3f-44b9-9b68-612f40779ce2, reasoning=false, effort=not specified, suffix=Non-reasoning). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Source model ID: artificial-analysis/b58b8272-cd3f-44b9-9b68-612f40779ce2/hy3-preview/hy3-non-reasoning. Source model name: Hy3-preview. Provider reported by source: Tencent. Model snapshot: Hy3-preview (Non-reasoning). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: non-reasoning. Reasoning effort: none. Score display: 0.3%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-critpt-v2:v2:standalone:non-reasoning:effort=unspecified:suffix=Non-reasoning
Comparison methodology: Exact AA configuration: Hy3-preview (Non-reasoning) (release hy3-preview, row hy3-non-reasoning, UUID b58b8272-cd3f-44b9-9b68-612f40779ce2, reasoning=false, effort=not specified, suffix=Non-reasoning). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: non-reasoning. Reasoning effort: none
Context: This AA source field contains the original CritPt score. The earlier CritPt v2 attribution was incorrect; the value and former label remain as disputed historical evidence.. The source dataset marks this result as disputed. It remains visible as documented evidence, but is not reliable comparative proof.

Source Artificial Analysis