Claude Opus 4.8 vs Grok 4.7
Wins 3 of 7 areas
Reasoning · Math · Long documents
Wins 4 of 7 areas
Coding · Agents · Facts · Following instructions
Grok 4.7 wins more areas, narrowly.Claude Opus 4.8 is better at reasoning.
Scores updated · 29 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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 software13Grok 4.73 of 4 tests
- AgentsCarrying out multi-step tasks on its own02Grok 4.72 of 2 tests
- FactsGetting facts right instead of making them up12Grok 4.72 of 3 tests
- Following instructionsDoing exactly what it is asked01Grok 4.71 of 1 test
- ReasoningHard problems that need careful thinking40Claude Opus 4.84 of 5 tests · 1 tie
- MathCompetition and research-level math21Claude Opus 4.82 of 3 tests
- Long documentsFinding answers in very long texts10Claude Opus 4.81 of 1 test
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 4.7 costs 73% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Grok 4.7 pulls ahead
- Real work tasks from 44 professionsGDPVal+12.8points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+10points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+4.1points ahead
Where Claude Opus 4.8 pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+39points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+27points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+10.7points ahead
Every test, side by side
All 29 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGrok 4.7
- LMArena · WebDevGrok 4.7 by 82 rating points15561638+82 rating
- LiveBench · CodingClaude Opus 4.8 by 4.681.877.2+4.6
- LiveBench · Agentic CodingGrok 4.7 by 3.550.554+3.5
- SciCodeGrok 4.7 by 354.457.4+3
AgentsGrok 4.7
- GDPValGrok 4.7 by 12.847.860.6+12.8
- Terminal-Bench 4.0Grok 4.7 by 4.121.725.8+4.1
ReasoningClaude Opus 4.8
- ARC-AGI-2Claude Opus 4.8 by 10.772.161.4+10.7
- LiveBench · ReasoningClaude Opus 4.8 by 6.589.282.7+6.5
- Humanity's Last ExamClaude Opus 4.8 by 5.648.743.1+5.6
- CritPtClaude Opus 4.8 by 3.220.917.7+3.2
- ARC-AGI-3tie1.51.8tie
FactsGrok 4.7
- AA-Omniscience · Non-hallucinationGrok 4.7 by 1060.770.7+10
- SimpleQA VerifiedGrok 4.7 by 35356+3
- AA-Omniscience · AccuracyClaude Opus 4.8 by 1.348.847.5+1.3
MathClaude Opus 4.8
- FrontierMath Tier 4Claude Opus 4.8 by 3956.117.1+39
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.8 by 278053+27
- LiveBench · MathematicsGrok 4.7 by 1.494.395.7+1.4
Following instructionsGrok 4.7
- LiveBench · Instruction FollowingGrok 4.7 by 3.37275.3+3.3
Other results10 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.
- SWE-MarathonGrok 4.7 by 202646+20
- Terminal-Bench 4.0Grok 4.7 by 14.423.638+14.4
- DeepSWE 1.1Grok 4.7 by 125971+12
- livebench_data_analysisGrok 4.7 by 10.96676.9+10.9
- AA IntelligenceGrok 4.7 by 4.641.846.4+4.6
- AA-OmniscienceGrok 4.7 by 3.228.832+3.2
- ARC-AGI-1Claude Opus 4.8 by 392.589.5+3
- CyberGymGrok 4.7 by 1.578.880.3+1.5
- HealthBench Professionaltie55.856.7tie
- livebench_languagetie79.780.1tie
Questions people ask
Which is better, Claude Opus 4.8 or Grok 4.7?
Grok 4.7 wins four of the seven areas where both have results: coding, agents, facts and following instructions. Claude Opus 4.8 wins reasoning, math and long documents.
Which is better for coding?
Grok 4.7. It wins 3 of the 4 coding tests both models report; Claude Opus 4.8 wins 1.
Which is cheaper?
Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Grok 4.7 costs $2.00 and $6.00. That makes Grok 4.7 about 73% cheaper for the same work.
How do you compare the two?
We use the 29 benchmark tests both models have published scores on. The verdict counts the 19 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.