Claude Opus 4.6 vs Grok 4
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents
Wins 0 of 8 areas
—
Claude Opus 4.6 is the stronger all-rounder.Grok 4 is cheaper.
Scores updated · 27 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 up20Claude Opus 4.62 of 3 tests · 1 tie
- CodingWriting and fixing software20Claude Opus 4.62 of 2 tests
- Images and chartsUnderstanding pictures, charts and video20Claude Opus 4.62 of 2 tests
- AgentsCarrying out multi-step tasks on its own10Claude Opus 4.61 of 1 test
- MathCompetition and research-level math10Claude Opus 4.61 of 1 test
- Long documentsFinding answers in very long texts10Claude Opus 4.61 of 1 test
- Following instructionsDoing exactly what it is asked00Even0 each · 1 tie
Agents, math, 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.
Grok 4 costs 40% 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+52.9points ahead
- Real work tasks from 44 professionsGDPVal+31.3points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+13.2points ahead
Where Grok 4 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 27 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 8.346.237.9+8.3
- SciCodeClaude Opus 4.6 by 6.251.945.7+6.2
ReasoningClaude Opus 4.6
- ARC-AGI-2Claude Opus 4.6 by 52.968.815.9+52.9
- Humanity's Last ExamClaude Opus 4.6 by 13.239.926.7+13.2
- CritPtClaude Opus 4.6 by 10.612.62+10.6
- GPQA DiamondClaude Opus 4.6 by 1.989.687.7+1.9
FactsClaude Opus 4.6
- AA-Omniscience · AccuracyClaude Opus 4.6 by 6.54740.5+6.5
- AA-Omniscience · Non-hallucinationClaude Opus 4.6 by 1.737.235.5+1.7
- SimpleQA Verifiedtie4747.9tie
Images and chartsClaude Opus 4.6
- LMArena · VisionClaude Opus 4.6 by 106 rating points13161210+106 rating
- MMMU-ProClaude Opus 4.6 by 6.675.468.8+6.6
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.
- ARC-AGI-1Claude Opus 4.6 by 26.39366.7+26.3
- AA Agentic IndexClaude Opus 4.6 by 26.167.641.5+26.1
- frontiermath_tier_4_v1Claude Opus 4.6 by 20.822.92.1+20.8
- τ²-Bench Telecom (AA run)Claude Opus 4.6 by 17.292.174.9+17.2
- AA-OmniscienceClaude Opus 4.6 by 11.613.72.1+11.6
- LiveCodeBenchClaude Opus 4.6 by 9.888.879+9.8
- AA IntelligenceClaude Opus 4.6 by 9.431.922.5+9.4
- AIME 2025Claude Opus 4.6 by 8.199.891.7+8.1
- HMMT Nov. 2025Claude Opus 4.6 by 896.388.3+8
- Artificial Analysis Coding IndexClaude Opus 4.6 by 7.648.140.5+7.6
- AIME25 no toolsClaude Opus 4.6 by 3.995.691.7+3.9
- matharena_visual_math_overallClaude Opus 4.6 by 2.372.370+2.3
Questions people ask
Which is better, Claude Opus 4.6 or Grok 4?
Claude Opus 4.6 wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and long documents. Grok 4 wins none, but costs 40% less. They are level on following instructions.
Which is better for coding?
Claude Opus 4.6. It wins 2 of the 2 coding tests both models report; Grok 4 wins none.
Which is cheaper?
Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; Grok 4 costs $3.00 and $15.00. That makes Grok 4 about 40% cheaper for the same work.
How do you compare the two?
We use the 27 benchmark tests both models have published scores on. The verdict counts the 15 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.