Agents-A1
InternScienceOpen weightsReasoningProvisionalReleased Jun 26, 2026
Overall score
54.4
Rank 71 of 222 · 40.0–68.7
Context window
262K
262,000 tokens
Price per 1M tokens
— in · — out
No price listed
Blended price
—
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Knowledge71.4
- 2Reasoning63.4
- 3Agentic & tool use60.6
Benchmark results (6)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Agentic & tool use
| BrowseComp | 75.5 | #29 of 50 |
| HLE w/ tools | 47.6 | #22 of 27 |
| VITA-Bench | 38.8 | #5 of 11 |
Reasoning
| LongBench v2 | 60.2 | #13 of 17 |
Knowledge
| HLE | 47.6 | #21 of 69 |
Instruction following
| IFEval | 94.8 | #3 of 53 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price | — | — | — |
Speed
Measured by us through OpenRouter (median of trials).
Not available on OpenRouter, so we cannot measure it yet.
Related models
Same family
Similar score
- Agents-A1-F16-GGUF54.4 · —
- Agents-A1-FP854.4 · —
- Agents-A1-Q4_K_M-GGUF54.4 · —
- Agents-A1-Q8_0-GGUF54.4 · —
- Gemini 3 Flash54.3 · $1.13