Claude Fable 5.1 vs Kimi K3
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Math · Following instructions
Wins 1 of 7 areas
Long documents
Claude Fable 5.1 is the stronger all-rounder.Kimi K3 is cheaper and better at long documents.
Both rank among the ten best models we track in agents and long documents.
Scores updated · 41 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.
- ReasoningHard problems that need careful thinking50Claude Fable 5.15 of 6 tests · 1 tie
- CodingWriting and fixing software50Claude Fable 5.15 of 5 tests
- AgentsCarrying out multi-step tasks on its own40Claude Fable 5.14 of 4 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
- Following instructionsDoing exactly what it is asked10Claude Fable 5.11 of 1 test
- Long documentsFinding answers in very long texts01Kimi K31 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.
Kimi K3 costs 70% 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+48.8points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+39.4points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+29.6points ahead
Where Kimi K3 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+19.4points ahead
- Reasons across sets of long documentsAA-LCR+3.4points ahead
Every test, side by side
All 41 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Fable 5.1
- LMArena · WebDevClaude Fable 5.1 by 88 rating points17431655+88 rating
- Terminal-Bench 2.1Claude Fable 5.1 by 6.491.485+6.4
- LiveBench · CodingClaude Fable 5.1 by 4.986.481.5+4.9
- LiveBench · Agentic CodingClaude Fable 5.1 by 3.966.162.2+3.9
- SciCodeClaude Fable 5.1 by 3.663.159.5+3.6
AgentsClaude Fable 5.1
- Terminal-Bench 4.0Claude Fable 5.1 by 39.45212.6+39.4
- GDPValClaude Fable 5.1 by 1162.751.7+11
- AA IT-Bench SREClaude Fable 5.1 by 1.849.547.7+1.8
- τ-Bench V3 · BankingClaude Fable 5.1 by 1.247.246+1.2
ReasoningClaude Fable 5.1
- ARC-AGI-2Claude Fable 5.1 by 29.69060.4+29.6
- SimpleBenchClaude Fable 5.1 by 25.986.660.7+25.9
- Humanity's Last ExamClaude Fable 5.1 by 12.259.146.9+12.2
- CritPtClaude Fable 5.1 by 6.329.723.4+6.3
- LiveBench · ReasoningClaude Fable 5.1 by 191.790.7+1
- GPQA Diamondtie93.793.5tie
FactsClaude Fable 5.1
- SimpleQA VerifiedClaude Fable 5.1 by 20.270.850.6+20.2
- AA-Omniscience · AccuracyClaude Fable 5.1 by 19.667.247.6+19.6
- AA-Omniscience · Non-hallucinationKimi K3 by 19.427.446.8+19.4
MathClaude Fable 5.1
- FrontierMath Tier 4Claude Fable 5.1 by 48.887.839+48.8
- FrontierMath Tiers 1-3 (v2)Claude Fable 5.1 by 1890.272.2+18
- LiveBench · MathematicsClaude Fable 5.1 by 12.69784.4+12.6
Following instructionsClaude Fable 5.1
- LiveBench · Instruction FollowingClaude Fable 5.1 by 1.67371.4+1.6
Other results18 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 43.255.812.6+43.2
- AA-OmniscienceClaude Fable 5.1 by 23.843.519.7+23.8
- OSWorld 2.0Claude Fable 5.1 by 19.677.958.3+19.6
- HiL-Bench (Tools-allowed)Claude Fable 5.1 by 18.861.542.7+18.8
- GDPval-AA v2Claude Fable 5.1 by 171 rating points18531682+171 rating
- GDPval-AA v2 EloClaude Fable 5.1 by 149 rating points18351686+149 rating
- AA IntelligenceClaude Fable 5.1 by 9.853.443.6+9.8
- Program BenchClaude Fable 5.1 by 9.887.677.8+9.8
- AA Agentic IndexClaude Fable 5.1 by 7.45850.6+7.4
- HLE (with tools)Claude Fable 5.1 by 5.865.659.8+5.8
- OfficeQA ProClaude Fable 5.1 by 5.76963.3+5.7
- Artificial Analysis Coding IndexClaude Fable 5.1 by 5.481.676.2+5.4
- livebench_languageClaude Fable 5.1 by 489.585.5+4
- PostTrainBenchClaude Fable 5.1 by 3.640.236.6+3.6
- ARC-AGI-1Claude Fable 5.1 by 397.594.5+3
- DeepSWE 1.1Kimi K3 by 1.667.469+1.6
- livebench_data_analysisClaude Fable 5.1 by 1.680.378.7+1.6
- Toolathlon VerifiedClaude Fable 5.1 by 1.377.876.5+1.3
Questions people ask
Which is better, Claude Fable 5.1 or Kimi K3?
Claude Fable 5.1 wins six of the seven areas where both have results: coding, agents, reasoning, facts, math and following instructions. Kimi K3 wins long documents, and costs 70% less.
Which is better for coding?
Claude Fable 5.1. It wins 5 of the 5 coding tests both models report; Kimi K3 wins none.
Which is cheaper?
Claude Fable 5.1 costs $10.00 per million input tokens and $50.00 per million output tokens; Kimi K3 costs $3.00 and $15.00. That makes Kimi K3 about 70% cheaper for the same work.
How do you compare the two?
We use the 41 benchmark tests both models have published scores on. The verdict counts the 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 18 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.