Cohereopen-weight
Released: 2025-03-13VerifiedCommand A+
Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...
Intelligence Index
—/ 100
Artificial Analysis Intelligence Index (independent composite)Throughput Speed
44tok/sec
Output streaming throughputTime to First Answer
8.6s
Time to first answer token, including any thinkingCost to Run the Index
—USD
Artificial Analysis cost of the full Index runMeasured results · Artificial Analysis
Independent evaluations of Command A+. Values are reported as published; nothing here is estimated or derived. Snapshot 2026-11-15.
- Intelligence Index
- —
- Cost to run the Index
- —
- Time per task
- —
- Omniscience index
- —
- Reasoning model
- No
- Cached-input price
- —
Reasoning & knowledge
- AIME 202513.0%
- CritPt0.0%
- GPQA Diamond52.7%
- Humanity's Last Exam4.0%
- IFBench36.5%
Coding & terminal agents
- LiveCodeBench28.7%
- Terminal-Bench Hard0.8%
Agentic work
- τ²-Bench Telecom15.2%
Long context & documents
Headline Evaluation Breakdown
Six independently measured evaluations (Artificial Analysis)Math · AIME 202513.0%
Long context · AA-LCR21.3%
Knowledge · Humanity's Last Exam4.0%
Instruction following · IFBench36.5%
Sourced Benchmark Evaluations (24)
Verified performance across authoritative benchmarks with provenance tracking.| Benchmark | Status | Score | Trust | Date | Source Type | Provenance |
|---|---|---|---|---|---|---|
| Terminal-Bench 4.0 | Active | 0.5% | 93 | 2026-11-15 | independent | Source ↗ |
| AutomationBench-AA | Active | 1.8% | 93 | 2026-11-15 | independent | Source ↗ |
| MLCR-AA (Medical Long Context Reasoning) | Active | 1.7% | 93 | 2026-11-15 | independent | Source ↗ |
| GDP.pdf | Active | 1% | 93 | 2026-11-15 | independent | Source ↗ |
| FrontierCode-AA 2.0 | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-Omniscience (Non-Hallucination) | Active | 86.1% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-Omniscience (Accuracy) | Active | 9.8% | 93 | 2026-11-15 | independent | Source ↗ |
| HLE-Diamond | Active | 5.1% | 93 | 2026-11-15 | independent | Source ↗ |
| CritPt v2 (Hard) | Active | 2.5% | 93 | 2026-11-15 | independent | Source ↗ |
| CritPt | Active | 0.3% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-LCR (Long Context Reasoning) | Active | 52.7% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench-Science 0.1 | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
| AIME | Nearing Saturation | 13% | 75 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench 2.1 | Active | 22.8% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench Hard | Active | 25% | 93 | 2026-11-15 | independent | Source ↗ |
| τ³-Banking | Active | 6% | 93 | 2026-11-15 | independent | Source ↗ |
| τ²-Bench Telecom | Active | 80.7% | 93 | 2026-11-15 | independent | Source ↗ |
| SciCode | Active | 38.5% | 93 | 2026-11-15 | independent | Source ↗ |
| IFBench | Active | 73.9% | 93 | 2026-11-15 | independent | Source ↗ |
| MMMU-Pro | Active | 63.2% | 93 | 2026-11-15 | independent | Source ↗ |
| LiveCodeBench | Saturated | 28.7% | 39 | 2026-11-15 | independent | Source ↗ |
| Humanity's Last Exam | Active | 12% | 93 | 2026-11-15 | independent | Source ↗ |
| GPQA | Nearing Saturation | 76.1% | 78 | 2026-11-15 | independent | Source ↗ |
| FrontierCode | Active | 1.2% | 98 | 2026-11-15 | independent | Source ↗ |
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run cohere-command-a
# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "cohere-command-a",
"messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
}'Evaluation & Sourcing Notes
Scores listed for Command A+ represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.
All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.