CohereCommand A+
Command A+ is a Cohere open-weights reasoning model, released 20 May 2026. Its best configuration ranks #368 of 785 on the BenchLeader Index at 50.5 ±7.8, in the upper half. The ± is the point: 434 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (72) and lowest in agents & tools (41). At $0.600 per million tokens blended it is mid-priced. Output speed of 149 tokens per second puts it in the fastest quarter, with a first answer in 14.0 s. Last measured 20 May 2026.
- Blended price
- $0.600/M
- $0.300 in · $1.50 out
- Output speed
- 149 tok/s
- measured by Artificial Analysis
- First answer
- 14 s
- first token 0.29 s
- Context
- 192k
- Full answer
- 17 s
- median, reasoning included
- Cost per run
- –
- Released
- 20 May 2026
- Overall index51
- Reasoning41
- Agents & tools41
- Knowledge60
- Instruction following72
- Multimodal46
- Long context51
- Composite44
How its index has moved
9 Sept 2026 to 23 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond (AA)not in index | 76.1%#240 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 12.0%#286 | Artificial Analysis | |
| CritPt | 0.3%#271 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| SciCode (AA)not in index | 38.5%#186 | Artificial Analysis | |
| Terminal-Bench 4.0 (AA)not in index | 0.5%#139 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 22.9%#169 | Artificial Analysis | |
| FrontierCode 1.1 (AA)not in index | 1.2%#68 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Terminal-Bench Hard | 25.0%#138 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 80.7%#121 | Artificial Analysis | |
| GDPval-AA v2.1not in index | 0.7%#121 | Artificial Analysis | |
| τ³-Banking (AA) | 6.0%#171 | Artificial Analysis | |
| AutomationBenchnot in index | 1.8%#184 | Artificial Analysis | |
| GDP.pdf (AA)not in index | 1.0%#204 | Artificial Analysis | |
| Terminal-Bench-Science 0.1 (AA)not in index | 0.0%#72 | Artificial Analysis |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -4.0#155 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 8.9%#509 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 85.8%#4 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 74.0%#37 | Artificial Analysis |
Multimodal
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MMMU-Pro | 63.2%#192 | Artificial Analysis |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 52.7%#314 | Artificial Analysis | |
| MLCRnot in index | 1.7%#163 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 13.1#314 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Cohere | 144 tok/s | 0.24 s | $0.300 | $1.50 | 192k | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0006 | – | 16.0 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0045 | – | 18.0 s |
| Code edit | 6,000 / 1,500 | $0.0041 | – | 24.1 s |
| Agentic coding session | 60,000 / 4,000 | $0.024 | – | 40.9 s |
| Structured extraction | 2,000 / 200 | $0.0009 | – | 15.3 s |
See also
Questions people ask
- What are Command A+'s benchmark scores?
- As of 25 Oct 2026, Command A+ scores 50.5 ±7.8 on the BenchLeader Index, strongest in instruction following (72) and weakest in agents & tools (41). That rests on 8 independent benchmark results, and every score on this page links to its publisher.
- How does Command A+ rank?
- Command A+ is #368 of 785 ranked configurations on 25 Oct 2026. 434 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Command A+ cost per 1M tokens?
- As of 25 Oct 2026, Command A+ costs $0.300 per 1M input tokens and $1.50 per 1M output tokens, $0.600 blended (three input tokens per output token).
- When was Command A+ released?
- Cohere released Command A+ on 20 May 2026.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Command A+: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/command-a-plus.