c4ai-command-a-03-2025: benchmark scores, price and ranking
c4ai-command-a-03-2025 from Cohere ranks #635 of 743 LLMs on the LLMs Tiger aggregate benchmark score (44.5), based on 3 benchmark results captured up to 2026-10-13.
- Organisation
- Cohere
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2025-03-13 (source: epoch)
- Aggregate rank
- #635 of 743 (score 44.5)
Relative to other models, c4ai-command-a-03-2025 is strongest on DTBench (#98 of 146) and weakest on LMCA (#94 of 108).
Across the 3 benchmarks where at least ten models are scored, c4ai-command-a-03-2025 is in the top 10% on 0 and in the top half on 0.
c4ai-command-a-03-2025 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| DTBench | 61.3% | #98 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 50.5% | #185 of 275 | HuggingFace GPQA Diamond leaderboard | 2026-10-13 |
| LMCA | 10.3% | #94 of 108 | Epoch AI Benchmarking Hub | 2026-10-13 |
About c4ai-command-a-03-2025
c4ai-command-a-03-2025 is an open-weight model that can run on your own hardware from Cohere. It was released on 2025-03-13, according to Epoch AI. No API price is listed for it yet. We hold 3 benchmark results for it across 3 areas, and none is in the top tenth of its board.
Where c4ai-command-a-03-2025 stands
On our aggregate score, c4ai-command-a-03-2025 is #635 of 743 ranked models, in the lower half. Its score is 44.5; the scale is centred on 50, so it sits 5.5 points below the typical model. That beats 15% of the ranked field. Among the 4 ranked Cohere models it is #4. The next one up is Command R+ (08-24) at 46.4.
c4ai-command-a-03-2025, benchmark by benchmark
c4ai-command-a-03-2025 lands below the middle on DTBench: 61.3%, #98 of 146, with 66% of the field scoring higher. Claude Opus 5.5 (max) leads at 98.9%; the closest result above is Llama-3.1-405B-Instruct at 61.4%. It covers dynamic tool-use benchmark. The board median is 68.8%, so c4ai-command-a-03-2025 is 7.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
c4ai-command-a-03-2025 lands below the middle on GPQA Diamond: 50.5%, #185 of 275, with 67% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is Llama-3.1-405B-Instruct at 50.9%. It covers expert-level science questions. The board median is 71.7%, so c4ai-command-a-03-2025 is 21.2 points below it. Source: HuggingFace GPQA Diamond leaderboard, captured 2026-10-13.
LMCA is a weak spot. c4ai-command-a-03-2025 scores 10.3%, #94 of 108, behind 86% of the models measured. The leader, Claude Opus 5.5 (max), reaches 68.2%. It covers language-model capability assessment. The board median is 29.2%, so c4ai-command-a-03-2025 is 18.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
c4ai-command-a-03-2025 has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.
Reading these numbers
The 3 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (2), HuggingFace GPQA Diamond leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 3 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #632 ollama/tulu3 (44.5)
- #633 qwen-turbo-2024-11-01 (44.5)
- #634 Mistral-7B-v0.2 (44.5)
- #636 DeepSeek-V3.2 (Thinking; Novita) (44.5)
- #637 mistral-small-3.1-2503 (44.4)
- #638 Yi-1.5-34B-Chat (44.4)
More from Cohere
- command-a-03-2025-quality (#445, 47.3)
- Command R (08-24) (#521, 46.4)
- Command R+ (08-24) (#522, 46.4)
Compare it on the live leaderboard → · How the aggregate score works