Claude Fable 5.1 vs Grok 4.7
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Math · Long documents
Wins 1 of 7 areas
Following instructions
Claude Fable 5.1 is the stronger all-rounder.Grok 4.7 is cheaper and better at following instructions.
Both rank among the ten best models we track in facts.
Scores updated · 27 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 software40Claude Fable 5.14 of 4 tests
- ReasoningHard problems that need careful thinking40Claude Fable 5.14 of 4 tests
- AgentsCarrying out multi-step tasks on its own30Claude Fable 5.13 of 3 tests
- MathCompetition and research-level math30Claude Fable 5.13 of 3 tests
- FactsGetting facts right instead of making them up21Claude Fable 5.12 of 3 tests
- Long documentsFinding answers in very long texts10Claude Fable 5.11 of 1 test
- Following instructionsDoing exactly what it is asked01Grok 4.71 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 87% 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 Fable 5.1 pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+70.7points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+37.2points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+28.6points ahead
Where Grok 4.7 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+43.3points ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+2.3points ahead
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 Fable 5.1
- LiveBench · Agentic CodingClaude Fable 5.1 by 12.166.154+12.1
- LMArena · WebDevClaude Fable 5.1 by 107 rating points17451638+107 rating
- LiveBench · CodingClaude Fable 5.1 by 9.286.477.2+9.2
- SciCodeClaude Fable 5.1 by 5.763.157.4+5.7
AgentsClaude Fable 5.1
- Terminal-Bench 4.0Claude Fable 5.1 by 26.25225.8+26.2
- AA IT-Bench SREClaude Fable 5.1 by 7.449.542.1+7.4
- GDPValClaude Fable 5.1 by 2.262.860.6+2.2
ReasoningClaude Fable 5.1
- ARC-AGI-2Claude Fable 5.1 by 28.69061.4+28.6
- Humanity's Last ExamClaude Fable 5.1 by 1659.143.1+16
- CritPtClaude Fable 5.1 by 1229.717.7+12
- LiveBench · ReasoningClaude Fable 5.1 by 991.782.7+9
FactsClaude Fable 5.1
- AA-Omniscience · Non-hallucinationGrok 4.7 by 43.327.470.7+43.3
- AA-Omniscience · AccuracyClaude Fable 5.1 by 19.767.247.5+19.7
- SimpleQA VerifiedClaude Fable 5.1 by 14.870.856+14.8
MathClaude Fable 5.1
- FrontierMath Tier 4Claude Fable 5.1 by 70.787.817.1+70.7
- FrontierMath Tiers 1-3 (v2)Claude Fable 5.1 by 37.290.253+37.2
- LiveBench · MathematicsClaude Fable 5.1 by 1.39795.7+1.3
Following instructionsGrok 4.7
- LiveBench · Instruction FollowingGrok 4.7 by 2.37375.3+2.3
Other results8 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.
- Terminal-Bench 4.0Claude Fable 5.1 by 17.855.838+17.8
- AA-OmniscienceClaude Fable 5.1 by 11.543.532+11.5
- livebench_languageClaude Fable 5.1 by 9.489.580.1+9.4
- ARC-AGI-1Claude Fable 5.1 by 897.589.5+8
- AA IntelligenceClaude Fable 5.1 by 753.446.4+7
- HealthBench ProfessionalClaude Fable 5.1 by 5.462.156.7+5.4
- DeepSWE 1.1Grok 4.7 by 3.667.471+3.6
- livebench_data_analysisClaude Fable 5.1 by 3.480.376.9+3.4
Questions people ask
Which is better, Claude Fable 5.1 or Grok 4.7?
Claude Fable 5.1 wins six of the seven areas where both have results: coding, agents, reasoning, facts, math and long documents. Grok 4.7 wins following instructions, and costs 87% less.
Which is better for coding?
Claude Fable 5.1. It wins 4 of the 4 coding tests both models report; Grok 4.7 wins none.
Which is cheaper?
Claude Fable 5.1 costs $10.00 per million input tokens and $50.00 per million output tokens; Grok 4.7 costs $2.00 and $6.00. That makes Grok 4.7 about 87% 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 19 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.