Cohere enterprise human evaluation
Cohere Command A 51.7% Dropped Trained annotators blindly compare two models' answers on enterprise tasks such as HR FAQs, technical FAQs and workplace assistants. They judge accuracy, instruction following and style. Results are win, tie and loss rates.
The Command A post reports six task groups and an average against GPT-4o (November 2024).
- Level
- Everyday Most adults, without training
- Scored
- Ranked by votes People pick the better of two answers, as in an arena, and the votes are turned into ratings.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
Cohere Command A leads with 51.7%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Cohere Command A | 51.7% | Mar 2025 | Model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No launch post has listed it since Mar 2025
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 13 Mar 2025 | Cohere Command A | 51.7 | Head-to-head human evaluation win rate vs GPT-4o (Nov), average of six enterprise task groups (tie 15.3) |
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 1 Apr 2025 | Cohere Command A technical report | Human pairwise win rate vs GPT-4o, three subsets with no overall (Table 23, Figure 1): General 50.4, Reasoning 51.4, Code 46.8 | Capabilities |
More in Economic work
- JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
- GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate.
Seed2.1 Pro 87.9% - GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
- AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
- CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished).
Qwen3.8-Omni-Flash 75.3% - OfficeQA In use Grounded reasoning over a large corpus of U.S. Treasury Bulletin documents: locate tables and compute precise numeric answers. Claude Opus 4.7 86.3%