Claude Fable 5 vs Kimi K2.7 Code
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Math · Long documents · Following instructions
Wins 0 of 7 areas
—
Claude Fable 5 is the stronger all-rounder.Kimi K2.7 Code is cheaper.
Scores updated · 36 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 software60Claude Fable 56 of 6 tests
- ReasoningHard problems that need careful thinking50Claude Fable 55 of 5 tests
- AgentsCarrying out multi-step tasks on its own40Claude Fable 54 of 4 tests
- FactsGetting facts right instead of making them up30Claude Fable 53 of 3 tests
- MathCompetition and research-level math30Claude Fable 53 of 3 tests
- Following instructionsDoing exactly what it is asked10Claude Fable 51 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude Fable 51 of 1 test
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.
Kimi K2.7 Code 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 Fable 5 pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+78points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+41.4points ahead
- Short factual questions, answered correctlySimpleQA Verified+34.2points ahead
Where Kimi K2.7 Code pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Fable 5
- Terminal-Bench HardClaude Fable 5 by 18.262.944.7+18.2
- Terminal-Bench 2.1Claude Fable 5 by 17.284.667.4+17.2
- LiveBench · Agentic CodingClaude Fable 5 by 16.562.245.7+16.5
- LMArena · WebDevClaude Fable 5 by 151 rating points16241473+151 rating
- SciCodeClaude Fable 5 by 13.26147.8+13.2
- LiveBench · CodingClaude Fable 5 by 128674+12
AgentsClaude Fable 5
- Terminal-Bench 4.0Claude Fable 5 by 41.442.41+41.4
- GDPValClaude Fable 5 by 28.655.627+28.6
- τ-Bench V3 · BankingClaude Fable 5 by 17.938.120.2+17.9
- MCP AtlasClaude Fable 5 by 8.784.776+8.7
ReasoningClaude Fable 5
- SimpleBenchClaude Fable 5 by 2481.957.9+24
- Humanity's Last ExamClaude Fable 5 by 20.555.535+20.5
- CritPtClaude Fable 5 by 18.628.610+18.6
- LiveBench · ReasoningClaude Fable 5 by 6.989.782.8+6.9
- GPQA DiamondClaude Fable 5 by 392.689.6+3
FactsClaude Fable 5
- SimpleQA VerifiedClaude Fable 5 by 34.270.736.5+34.2
- AA-Omniscience · AccuracyClaude Fable 5 by 25.865.339.6+25.8
- AA-Omniscience · Non-hallucinationClaude Fable 5 by 18.836.417.6+18.8
MathClaude Fable 5
- FrontierMath Tier 4Claude Fable 5 by 7890.212.2+78
- FrontierMath Tiers 1-3 (v2)Claude Fable 5 by 338754+33
- LiveBench · MathematicsClaude Fable 5 by 16.49679.6+16.4
Following instructionsClaude Fable 5
- LiveBench · Instruction FollowingClaude Fable 5 by 19.575.856.3+19.5
- IFBenchtie63.563.1tie
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 Fable 5 by 53.543.3-10.2+53.5
- DeepSWE 1.1Claude Fable 5 by 397031+39
- Program BenchClaude Fable 5 by 32.786.353.6+32.7
- AA Agentic IndexClaude Fable 5 by 28.55122.5+28.5
- AA IntelligenceClaude Fable 5 by 23.849.625.8+23.8
- livebench_data_analysisClaude Fable 5 by 17.880.562.7+17.8
- Artificial Analysis Coding IndexClaude Fable 5 by 15.776.560.8+15.7
- MLS Bench Litelower is betterKimi K2.7 Code by 14.849.935.1+14.8
- livebench_languageClaude Fable 5 by 12.890.777.9+12.8
- τ²-Bench Telecom (AA run)Claude Fable 5 by 8.498.590.1+8.4
- LiveBenchClaude Fable 5 by 6.478.371.9+6.4
- MCP Mark VerifiedClaude Fable 5 by 6.387.481.1+6.3
Questions people ask
Which is better, Claude Fable 5 or Kimi K2.7 Code?
Claude Fable 5 wins all seven areas where both have results: coding, agents, reasoning, facts, math, long documents and following instructions. Kimi K2.7 Code wins none, but costs 92% less.
Which is better for coding?
Claude Fable 5. It wins 6 of the 6 coding tests both models report; Kimi K2.7 Code wins none.
Which is cheaper?
Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Kimi K2.7 Code costs $0.95 and $4.00. That makes Kimi K2.7 Code about 92% cheaper for the same work.
How do you compare the two?
We use the 36 benchmark tests both models have published scores on. The verdict counts the 24 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.