Claude Opus 4.5 vs Devstral Medium
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
Claude Opus 4.5 is the stronger all-rounder.Devstral Medium is cheaper.
Scores updated · 17 tests both models report · How we compare
Where each one wins
Tests won in each of the six areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- CodingWriting and fixing software40Claude Opus 4.54 of 4 tests
- ReasoningHard problems that need careful thinking30Claude Opus 4.53 of 3 tests
- FactsGetting facts right instead of making them up20Claude Opus 4.52 of 2 tests
- AgentsCarrying out multi-step tasks on its own10Claude Opus 4.51 of 1 test
- Long documentsFinding answers in very long texts10Claude Opus 4.51 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Opus 4.51 of 1 test
Agents, long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Devstral Medium costs 92% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude Opus 4.5 pulls ahead
- Reasons across sets of long documentsAA-LCR+45.3points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+37.9points ahead
- Real work tasks from 44 professionsGDPVal+37.7points ahead
Where Devstral Medium pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 17 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.5
- LMArena · WebDevClaude Opus 4.5 by 390 rating points14691079+390 rating
- Terminal-Bench HardClaude Opus 4.5 by 37.9479.1+37.9
- SciCodeClaude Opus 4.5 by 20.149.529.4+20.1
- SWE-bench VerifiedClaude Opus 4.5 by 19.380.961.6+19.3
ReasoningClaude Opus 4.5
- GPQA DiamondClaude Opus 4.5 by 37.486.649.2+37.4
- Humanity's Last ExamClaude Opus 4.5 by 26.330.13.8+26.3
- CritPtClaude Opus 4.5 by 4.64.60+4.6
FactsClaude Opus 4.5
- AA-Omniscience · AccuracyClaude Opus 4.5 by 27.746.618.9+27.7
- AA-Omniscience · Non-hallucinationClaude Opus 4.5 by 1.23937.8+1.2
Following instructionsClaude Opus 4.5
- IFBenchClaude Opus 4.5 by 28.15829.9+28.1
Other results5 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- τ²-Bench Telecom (AA run)Claude Opus 4.5 by 69.689.519.9+69.6
- AA-OmniscienceClaude Opus 4.5 by 45.614-31.6+45.6
- AA Agentic IndexClaude Opus 4.5 by 43.859.615.8+43.8
- Artificial Analysis Coding IndexClaude Opus 4.5 by 31.947.815.9+31.9
- AA IntelligenceClaude Opus 4.5 by 20.129.19+20.1
Questions people ask
Which is better, Claude Opus 4.5 or Devstral Medium?
Claude Opus 4.5 wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. Devstral Medium wins none, but costs 92% less.
Which is better for coding?
Claude Opus 4.5. It wins 4 of the 4 coding tests both models report; Devstral Medium wins none.
Which is cheaper?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; Devstral Medium costs $0.40 and $2.00. That makes Devstral Medium about 92% cheaper for the same work.
How do you compare the two?
We use the 17 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 5 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.