Claude Fable 5.1 vs Gemini 4 Argon
Wins 3 of 6 areas
Coding · Math · Long documents
Wins 1 of 6 areas
Facts
Claude Fable 5.1 wins more areas, narrowly.Gemini 4 Argon is cheaper and better at facts.
Both rank among the ten best models we track in facts.
Scores updated · 46 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 software20Claude Fable 5.12 of 2 tests
- MathCompetition and research-level math20Claude Fable 5.12 of 2 tests
- Long documentsFinding answers in very long texts10Claude Fable 5.11 of 1 test
- FactsGetting facts right instead of making them up12Gemini 4 Argon2 of 3 tests
- AgentsCarrying out multi-step tasks on its own11Even1 each
- ReasoningHard problems that need careful thinking22Even2 each
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.
Gemini 4 Argon costs 80% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Fable 5.1 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+17.3points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+9.7points ahead
- Real work tasks from 44 professionsGDPVal+6.5points ahead
Where Gemini 4 Argon pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+57.5points ahead
- Short factual questions, answered correctlySimpleQA Verified+5.2points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+5.1points ahead
Every test, side by side
All 46 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 64 rating points17431679+64 rating
- SciCodeClaude Fable 5.1 by 1.363.161.8+1.3
AgentsEven
- GDPValClaude Fable 5.1 by 6.562.756.2+6.5
- Terminal-Bench 4.0Gemini 4 Argon by 5.15257.1+5.1
ReasoningEven
- SimpleBenchGemini 4 Argon by 5.186.691.7+5.1
- CritPtClaude Fable 5.1 by 2.629.727.1+2.6
- Humanity's Last ExamClaude Fable 5.1 by 259.157.1+2
- ARC-AGI-2Gemini 4 Argon by 1.39091.3+1.3
FactsGemini 4 Argon
- AA-Omniscience · Non-hallucinationGemini 4 Argon by 57.527.484.9+57.5
- AA-Omniscience · AccuracyClaude Fable 5.1 by 17.367.249.9+17.3
- SimpleQA VerifiedGemini 4 Argon by 5.270.876+5.2
MathClaude Fable 5.1
- FrontierMath Tier 4Claude Fable 5.1 by 9.787.878+9.7
- FrontierMath Tiers 1-3 (v2)Claude Fable 5.1 by 4.290.286+4.2
Other results32 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.
- AutomationBench (Score)Gemini 4 Argon by 19.931.451.3+19.9
- Knowledge work (AutomationBench)Gemini 4 Argon by 19.931.451.3+19.9
- GraphWalks (256k to 1M, BFS (F1))Gemini 4 Argon by 19.26584.2+19.2
- LVBenchGemini 4 Argon by 1279.791.7+12
- Multimodal understanding (LVBench)Gemini 4 Argon by 1279.791.7+12
- DeepSWE 1.1Gemini 4 Argon by 10.567.477.9+10.5
- RiemannBenchGemini 4 Argon by 10.465.676+10.4
- Science and math (RiemannBench)Gemini 4 Argon by 10.465.676+10.4
- Cybersecurity (CWE-bench v1)Gemini 4 Argon by 105868+10
- Cybersecurity (CWE-bench)Gemini 4 Argon by 105868+10
- Science and math (Terminal-Bench-Science 0.1 (AA))Gemini 4 Argon by 9.643.352.9+9.6
- Terminal-Bench-Science 0.1Gemini 4 Argon by 9.643.352.9+9.6
- OSWorld 2.0Claude Fable 5.1 by 8.777.969.2+8.7
- GraphWalks (Up to 128k, BFS (F1))Gemini 4 Argon by 8.391.499.7+8.3
- HealthBenchClaude Fable 5.1 by 8.157.249.1+8.1
- Agentic coding (Terminal-Bench 4.0 (AA))Gemini 4 Argon by 5.15257.1+5.1
- PostTrainBenchGemini 4 Argon by 5.140.245.3+5.1
- Science and math (Terminal-Bench Science 0.1)Gemini 4 Argon by 552.657.6+5
- GDP (Surge AI)Claude Fable 5.1 by 4.426.221.8+4.4
- HLE-DiamondClaude Fable 5.1 by 3.460.156.7+3.4
- Knowledge work (Vals Index)Gemini 4 Argon by 3.165.868.9+3.1
- Vals IndexGemini 4 Argon by 3.165.868.9+3.1
- HealthBench ProfessionalClaude Fable 5.1 by 2.757.855.1+2.7
- Computer use (OSWorld-2.1)Claude Fable 5.1 by 2.176.874.7+2.1
- Terminal-Bench 4.0Gemini 4 Argon by 1.655.857.4+1.6
- AA-OmniscienceClaude Fable 5.1 by 1.143.542.4+1.1
- ARC-AGI-1Gemini 4 Argon by 197.598.5+1
- General capabilities (AA Index v5.0)Gemini 4 Argon by 14950+1
- AA Intelligencetie53.452.6tie
- Agentic coding (Terminal-bench 4.0)tie57.957.4tie
- HiL-Bench (Tools-allowed)tie61.562tie
- CritPt v2 Hardtie52.552.5tie
Questions people ask
Which is better, Claude Fable 5.1 or Gemini 4 Argon?
Claude Fable 5.1 wins three of the six areas where both have results: coding, math and long documents. Gemini 4 Argon wins facts, and costs 80% less. They are level on agents and reasoning.
Which is better for coding?
Claude Fable 5.1. It wins 2 of the 2 coding tests both models report; Gemini 4 Argon wins none.
Which is cheaper?
Claude Fable 5.1 costs $10.00 per million input tokens and $50.00 per million output tokens; Gemini 4 Argon costs $2.00 and $10.00. That makes Gemini 4 Argon about 80% cheaper for the same work.
How do you compare the two?
We use the 46 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 32 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.