Claude Fable 5 vs Gemma 4 31B
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents
Wins 1 of 7 areas
Following instructions
Claude Fable 5 is the stronger all-rounder.Gemma 4 31B is cheaper and better at following instructions.
Scores updated · 35 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 software70Claude Fable 57 of 7 tests
- AgentsCarrying out multi-step tasks on its own50Claude Fable 55 of 5 tests
- ReasoningHard problems that need careful thinking30Claude Fable 53 of 3 tests
- FactsGetting facts right instead of making them up30Claude Fable 53 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20Claude Fable 52 of 2 tests
- Long documentsFinding answers in very long texts10Claude Fable 51 of 1 test
- Following instructionsDoing exactly what it is asked01Gemma 4 31B1 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.
Gemma 4 31B costs 99% 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
- Short factual questions, answered correctlySimpleQA Verified+60.3points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+50.4points ahead
- Real work tasks from 44 professionsGDPVal+49.5points ahead
Where Gemma 4 31B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+12.1points ahead
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Fable 5
- SWE-bench VerifiedClaude Fable 5 by 48.99546.1+48.9
- SWE-bench ProClaude Fable 5 by 44.38035.7+44.3
- SWE-bench MultilingualClaude Fable 5 by 43.686.643+43.6
- Terminal-Bench 2.1Claude Fable 5 by 41.284.643.4+41.2
- Terminal-Bench HardClaude Fable 5 by 26.562.936.4+26.5
- LMArena · WebDevClaude Fable 5 by 261 rating points16261365+261 rating
- SciCodeClaude Fable 5 by 15.56145.5+15.5
AgentsClaude Fable 5
- BrowseCompClaude Fable 5 by 50.487.437+50.4
- GDPValClaude Fable 5 by 49.555.56+49.5
- Terminal-Bench 4.0Claude Fable 5 by 42.442.40+42.4
- MCP AtlasClaude Fable 5 by 30.584.754.2+30.5
- τ-Bench V3 · BankingClaude Fable 5 by 23.338.114.8+23.3
ReasoningClaude Fable 5
- Humanity's Last ExamClaude Fable 5 by 31.955.523.6+31.9
- CritPtClaude Fable 5 by 27.228.61.4+27.2
- GPQA DiamondClaude Fable 5 by 6.992.685.7+6.9
FactsClaude Fable 5
- SimpleQA VerifiedClaude Fable 5 by 60.370.710.4+60.3
- AA-Omniscience · AccuracyClaude Fable 5 by 45.465.320+45.4
- AA-Omniscience · Non-hallucinationClaude Fable 5 by 21.436.415+21.4
Images and chartsClaude Fable 5
- MMMU-ProClaude Fable 5 by 10.884.273.4+10.8
- LMArena · VisionClaude Fable 5 by 46 rating points13251279+46 rating
Following instructionsGemma 4 31B
- IFBenchGemma 4 31B by 12.163.575.6+12.1
Other results13 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.
- GDPval-AA 2.1Claude Fable 5 by 968 rating points1595627+968 rating
- AA-OmniscienceClaude Fable 5 by 91.243.3-47.9+91.2
- JobBenchClaude Fable 5 by 49.257.48.2+49.2
- WideSearchClaude Fable 5 by 4681.235.2+46
- Terminal-Bench 4.0Claude Fable 5 by 44.544.50+44.5
- AA Agentic IndexClaude Fable 5 by 44.3516.7+44.3
- τ²-Bench Telecom (AA run)Claude Fable 5 by 38.698.559.9+38.6
- HLE (with tools)Claude Fable 5 by 37.363.826.5+37.3
- AA IntelligenceClaude Fable 5 by 34.949.614.7+34.9
- Artificial Analysis Coding IndexClaude Fable 5 by 33.176.543.4+33.1
- DeepSearchQA (F1)Claude Fable 5 by 32.594.261.7+32.5
- Terminal-Bench-Science 0.1Claude Fable 5 by 24.724.70+24.7
- GDP (Surge AI)Claude Fable 5 by 23.829.86+23.8
Questions people ask
Which is better, Claude Fable 5 or Gemma 4 31B?
Claude Fable 5 wins six of the seven areas where both have results: coding, agents, reasoning, facts, images and charts and long documents. Gemma 4 31B wins following instructions, and costs 99% less.
Which is better for coding?
Claude Fable 5. It wins 7 of the 7 coding tests both models report; Gemma 4 31B wins none.
Which is cheaper?
Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Gemma 4 31B costs $0.15 and $0.40. That makes Gemma 4 31B about 99% cheaper for the same work.
How do you compare the two?
We use the 35 benchmark tests both models have published scores on. The verdict counts the 22 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.