Mercury 2.5
Inception · Proprietary · bench-align-v5
Capability 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.
| Component | USD | Evidence |
|---|---|---|
| Input / 1M tokens | $0.04 | |
| Output / 1M tokens | $0.15 | |
| Cache read / 1M tokens | $0.004 | |
| Cache write / 1M tokens | Unavailable | |
| Blended / 1M (75% input / 25% output) | $0.0675 |
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
8 matched benchmark rows with their published value, unit, and provenance.
Knowledge
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| GPQA-D GPQA Diamond | 79.0 | Graduate-level science questions | Graduate level | Trinity-Large-Thinking: Scaling an Open Source Frontier Agent |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 22.0 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 67.0 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
Coding
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| SciCode Scientific Code Benchmark | 38 | — | — | BenchLM |
Reasoning
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| AA-LCR Artificial Analysis Long Context Reasoning | 68.0 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
Instruction Following
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| IFBench Instruction Following Benchmark | 77 | — | — | BenchLM |
Agentic
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| DeepSearchQA DeepSearchQA | 34.0 | Agentic browsing and list-answer questions | Agentic web research | Muse Spark Eval Methodology |
| τ³-bench results τ³-Bench Tool-Agent-User Evaluation | 96.0 | Corrected customer-service tasks plus knowledge and voice evaluation modes | Long-horizon, multimodal, and knowledge-aware tool use | Official τ³-bench repository and release notes |
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.