Claude Fable 5 vs Inkling-Small
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents
Wins 1 of 8 areas
Following instructions
Claude Fable 5 is the stronger all-rounder.Inkling-Small is cheaper and better at following instructions.
Scores updated · 37 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.
- CodingWriting and fixing software50Claude Fable 55 of 5 tests
- AgentsCarrying out multi-step tasks on its own50Claude Fable 55 of 5 tests
- ReasoningHard problems that need careful thinking40Claude Fable 54 of 4 tests
- FactsGetting facts right instead of making them up20Claude Fable 52 of 3 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video20Claude Fable 52 of 2 tests
- MathCompetition and research-level math20Claude Fable 52 of 2 tests
- Long documentsFinding answers in very long texts10Claude Fable 51 of 1 test
- Following instructionsDoing exactly what it is asked01Inkling-Small1 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.
Inkling-Small costs 98% 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+73.1points ahead
- Short factual questions, answered correctlySimpleQA Verified+50.1points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+49.1points ahead
Where Inkling-Small pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+18.7points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Fable 5
- Terminal-Bench 2.1Claude Fable 5 by 29.584.655.1+29.5
- SWE-bench ProClaude Fable 5 by 24.18055.9+24.1
- LMArena · WebDevClaude Fable 5 by 215 rating points16241409+215 rating
- SWE-bench VerifiedClaude Fable 5 by 14.89580.2+14.8
- SciCodeClaude Fable 5 by 11.36149.7+11.3
AgentsClaude Fable 5
- Terminal-Bench 4.0Claude Fable 5 by 41.442.41+41.4
- GDPValClaude Fable 5 by 24.455.631.2+24.4
- τ-Bench V3 · BankingClaude Fable 5 by 19.338.118.8+19.3
- BrowseCompClaude Fable 5 by 1087.477.4+10
- MCP AtlasClaude Fable 5 by 5.184.779.6+5.1
ReasoningClaude Fable 5
- ARC-AGI-2Claude Fable 5 by 49.189.240.1+49.1
- Humanity's Last ExamClaude Fable 5 by 22.255.533.3+22.2
- CritPtClaude Fable 5 by 20.328.68.3+20.3
- GPQA DiamondClaude Fable 5 by 3.192.689.5+3.1
FactsClaude Fable 5
- SimpleQA VerifiedClaude Fable 5 by 50.170.720.6+50.1
- AA-Omniscience · AccuracyClaude Fable 5 by 32.265.333.2+32.2
- AA-Omniscience · Non-hallucinationtie36.437tie
Images and chartsClaude Fable 5
- MMMU-ProClaude Fable 5 by 10.284.274+10.2
- LMArena · VisionClaude Fable 5 by 91 rating points13251234+91 rating
MathClaude Fable 5
- FrontierMath Tier 4Claude Fable 5 by 73.190.217.1+73.1
- FrontierMath Tiers 1-3 (v2)Claude Fable 5 by 40.78746.3+40.7
Following instructionsInkling-Small
- IFBenchInkling-Small by 18.763.582.2+18.7
Other results14 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 52.243.3-8.9+52.2
- GDPval-AA v2Claude Fable 5 by 485 rating points17231238+485 rating
- AA Agentic IndexClaude Fable 5 by 265125+26
- SWEBench Pro PublicClaude Fable 5 by 24.18055.9+24.1
- AA IntelligenceClaude Fable 5 by 23.949.625.7+23.9
- Artificial Analysis Coding IndexClaude Fable 5 by 23.676.552.9+23.6
- Toolathlon VerifiedClaude Fable 5 by 23.577.954.4+23.5
- HLE (with tools)Claude Fable 5 by 1663.847.8+16
- ARC-AGI-1Claude Fable 5 by 14.598.584+14.5
- τ³-Bench BankingClaude Fable 5 by 11.326.815.5+11.3
- charxiv_rq_with_pythonClaude Fable 5 by 8.189.481.3+8.1
- ToolathlonClaude Fable 5 by 7.361.754.4+7.3
- Global-MMLU-LiteClaude Fable 5 by 6.693.386.7+6.6
- StrongREJECTtie98.798.4tie
Questions people ask
Which is better, Claude Fable 5 or Inkling-Small?
Claude Fable 5 wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and long documents. Inkling-Small wins following instructions, and costs 98% less.
Which is better for coding?
Claude Fable 5. It wins 5 of the 5 coding tests both models report; Inkling-Small wins none.
Which is cheaper?
Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Inkling-Small costs $0.30 and $1.20. That makes Inkling-Small about 98% cheaper for the same work.
How do you compare the two?
We use the 37 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 14 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.