Claude Opus 4.6 vs o4-mini
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents
Wins 1 of 8 areas
Following instructions
Claude Opus 4.6 is the stronger all-rounder.o4-mini is cheaper and better at following instructions.
Scores updated · 33 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- ReasoningHard problems that need careful thinking40Claude Opus 4.64 of 4 tests
- FactsGetting facts right instead of making them up40Claude Opus 4.64 of 4 tests
- CodingWriting and fixing software30Claude Opus 4.63 of 3 tests
- Images and chartsUnderstanding pictures, charts and video30Claude Opus 4.63 of 3 tests
- AgentsCarrying out multi-step tasks on its own20Claude Opus 4.62 of 2 tests
- MathCompetition and research-level math20Claude Opus 4.62 of 2 tests
- Long documentsFinding answers in very long texts10Claude Opus 4.61 of 1 test
- Following instructionsDoing exactly what it is asked02o4-mini2 of 2 tests
Long documents rests on a single test.
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.
o4-mini costs 82% 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 4.6 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+62.7points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+32.5points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+31points ahead
Where o4-mini pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+15.6points ahead
- Keeps track of context across a multi-turn chatMulti-Challenge+5.8points ahead
Every test, side by side
All 33 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.6
- Terminal-Bench HardClaude Opus 4.6 by 3146.215.2+31
- SWE-bench VerifiedClaude Opus 4.6 by 12.780.868.1+12.7
- SciCodeClaude Opus 4.6 by 5.451.946.5+5.4
AgentsClaude Opus 4.6
- BrowseCompClaude Opus 4.6 by 32.58451.5+32.5
- GDPValClaude Opus 4.6 by 30.555.925.4+30.5
ReasoningClaude Opus 4.6
- ARC-AGI-2Claude Opus 4.6 by 62.768.86.1+62.7
- Humanity's Last ExamClaude Opus 4.6 by 23.439.916.5+23.4
- CritPtClaude Opus 4.6 by 1212.60.6+12
- GPQA DiamondClaude Opus 4.6 by 11.289.678.4+11.2
FactsClaude Opus 4.6
- SimpleQA VerifiedClaude Opus 4.6 by 28.24718.8+28.2
- AA-Omniscience · AccuracyClaude Opus 4.6 by 22.24724.8+22.2
- AA-Omniscience · Non-hallucinationClaude Opus 4.6 by 17.737.219.5+17.7
- Vectara HHEM hallucination ratelower is betterClaude Opus 4.6 by 6.412.218.6+6.4
Images and chartsClaude Opus 4.6
- LMArena · VisionClaude Opus 4.6 by 122 rating points13161194+122 rating
- MMMU-ProClaude Opus 4.6 by 6.275.469.2+6.2
- CharXiv (RQ)Claude Opus 4.6 by 5.477.472+5.4
MathClaude Opus 4.6
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.6 by 29.96636.1+29.9
- FrontierMath Tier 4Claude Opus 4.6 by 21.926.84.9+21.9
Following instructionso4-mini
- IFBencho4-mini by 15.653.168.7+15.6
- Multi-Challengeo4-mini by 5.837.143+5.8
Other results12 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.
- AA-OmniscienceClaude Opus 4.6 by 49.413.7-35.7+49.4
- τ²-Bench Telecom (AA run)Claude Opus 4.6 by 36.592.155.6+36.5
- ARC-AGI-1Claude Opus 4.6 by 34.39358.7+34.3
- AA Agentic IndexClaude Opus 4.6 by 31.567.636.1+31.5
- Artificial Analysis Coding IndexClaude Opus 4.6 by 22.548.125.6+22.5
- frontiermath_tier_4_v1Claude Opus 4.6 by 16.622.96.3+16.6
- AA IntelligenceClaude Opus 4.6 by 15.231.916.7+15.2
- LiveCodeBenchClaude Opus 4.6 by 11.488.877.4+11.4
- AIME 2025Claude Opus 4.6 by 7.199.892.7+7.1
- vectara_factual_consistencyClaude Opus 4.6 by 6.487.881.4+6.4
- vectara_avg_summary_lengthtie137.6127.7tie
- vectara_answer_ratetie99.899.2tie
Questions people ask
Which is better, Claude Opus 4.6 or o4-mini?
Claude Opus 4.6 wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and long documents. o4-mini wins following instructions, and costs 82% less.
Which is better for coding?
Claude Opus 4.6. It wins 3 of the 3 coding tests both models report; o4-mini wins none.
Which is cheaper?
Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; o4-mini costs $1.10 and $4.40. That makes o4-mini about 82% cheaper for the same work.
How do you compare the two?
We use the 33 benchmark tests both models have published scores on. The verdict counts the 21 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.