Agents-A1-4B
InternScience · Open Weight · bench-align-v5
Self-hostedCapability shape
Seven axes from the ranking source. A missing axis is drawn as a gap.
Runtime service evidence
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: ObservedUnavailable
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | Unavailable | Unavailable | Unavailable | |
| Throughput | Unavailable | Unavailable | Unavailable |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
Endpoint and price matrix
Every published price component, including cache reads and writes.
Workload-aware monthly cost example
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
Benchmark record
11 matched benchmark rows with their published value, unit, and provenance.
Knowledge
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| FrontierScience Research FrontierScience Research | 33.3 | Scientific research problems | Frontier scientific research | Muse Spark Eval Methodology |
Coding
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| LiveCodeBench v6 LiveCodeBench v6 | 59.6 | Fresh programming problems | Competitive programming level | LiveCodeBench official repository and release documentation |
| SciCode Scientific Code Benchmark | 29.6 | — | — | BenchLM |
Reasoning
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| LongBench v2 LongBench v2 | 52.1 | Long-context tasks | Hard long-context | LongBench v2 |
Instruction Following
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| IFEval Instruction-Following Eval | 94.8 | 541 prompts across 25 instruction types | Instruction precision | Instruction-Following Evaluation for Large Language Models |
| IFBench Instruction Following Benchmark | 69.1 | — | — | BenchLM |
Agentic
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| BrowseComp BrowseComp | 66.8 | Research questions requiring browsing | Hard web research | BrowseComp |
| τ²-bench results τ²-Bench Tool-Agent-User Evaluation | 78.2 | Airline, retail, and telecom customer-service task sets | Dual-control customer-service workflows | τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment |
| MLE-Bench Lite MLE-Bench Lite | 22.7 | Low-resource ML competitions | Agentic machine learning | MiniMax M2.7: Early Echoes of Self-Evolution |
| VITA-Bench VITA-Bench | 40.3 | Interactive consumer-service agent tasks | Long-horizon real-world workflows | VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications |
| GAIA General AI Assistants | 95.1 | — | — | BenchLM |
Lifecycle and limitations log
Lifecycle events the source associates with this model, plus what this profile does not claim.
That is not evidence the model has no lifecycle plan — only that this source published none.