Modelsby GlyphCohere vs Microsoft
Each lab shows its best-ranked model on every board. One row per board where at least one is ranked, from each board's current capture.
Head to head on 2 boards: Cohere places best on 1 and Microsoft places best on 1. Both ranked on 2 of 10 boards.
| Board | |||
|---|---|---|---|
| Reasoning2 | |||
| Nov 9today | #426.2Command A+ | ||
| Nov 9today | #7576.0%Phi 4 Plus | ||
| Coding1 | |||
| Nov 9today | #4512.0%Command A 03 2025 Quality | ||
| Agents and tools1 | |||
| Nov 9today | #1157.1%best of the pickedCommand A+ | #5028.8%Phi 4 | |
| Image2 | |||
| Nov 9today | #41,467MAI Image 2.7 | ||
| Nov 9today | #61,330MAI Image 2.6 | ||
| Speech2 | |||
| Nov 9today | #146.72 WERcohere-transcribe-03-2026 (CohereLabs) | #35.55 WERbest of the pickedazure-speech-09-2026 (microsoft) | |
| Nov 9today | #311,145Azure Hd 2.5 | ||
| Embeddings1 | |||
| Nov 9today | #174.3%harrier-oss-v1-27b (microsoft) | ||
| Speed1 | |||
| Nov 9today | #394 tok/sNorth Mini Code |
Green marks the best placing among the picked where two or more are ranked; ties are marked for each. Ranks are each board's own order (lower is better), scores as the board published them. Dash: not on that board.
More comparisons
- GPT vs ClaudeGPT-6 Astra and Claude Fable 5.1, the top-ranked of each
- Claude vs GeminiClaude Fable 5.1 and Gemini 4 Argon, the top-ranked of each
- OpenAI vs Anthropic vs GoogleEach lab's best-ranked model on every board
- Open-weight vs closedThe best open-weight model on every board against the best closed one