Claude Fable 5 vs Gemini 4 Argon
| Spec | Claude Fable 5 | Gemini 4 Argon |
|---|---|---|
| Respan Index | 63.9 (#18) | 69.2 (#13) |
| Blended price per 1M | $20 | $4 |
| Context window | 1M | - |
| Input / output per 1M | $10 / $50 | $2 / $10 |
| Max output | 128K | 1M |
| Input | text, vision | text, vision, video |
| Released | 2026-06-09 | 2026-09-30 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Claude Fable 5 | Gemini 4 Argon |
|---|---|---|
| Coding | 54.3 Claude Fable 5 | 55.3 Gemini 4 Argon |
| Agents | 67.9 Claude Fable 5 | 77.5 Gemini 4 Argon |
| Reasoning | 70.1 Claude Fable 5 | 78.6 Gemini 4 Argon |
| Knowledge & language | 72.4 Claude Fable 5 | 76.0 Gemini 4 Argon |
| Human preference | 57.1 Claude Fable 5 | 58.4 Gemini 4 Argon |
Benchmarks both report
Gemini 4 Argon leads on 16 of the 20 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Fable 5 | Gemini 4 Argon |
|---|---|---|
| LMArena Elo | 1504 | 1520 |
| LMArena WebDev (LMArena) | 1626 | 1681 |
| LMArena Agent (LMArena) | 0.0586 | 0.1031 |
| MirrorCode (Epoch AI) | 70% | 58.9% |
| Chess Puzzles (Epoch AI) | 47% | 59% |
| APEX-Agents (Mercor) | 63.6% | 82.4% |
| EBR-bench (Epoch AI) | 39.5% | 64.8% |
| FrontierMath Tier 4 v2 (Epoch AI) | 90.2% | 78% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 87% | 86% |
| FrontierSWE V2 (Proximal Labs) | 47% | 55% |
| Furniture Assembly (Epoch AI) | 35.8% | 72.5% |
| GPQA Diamond | 85.9% | 96.4% |
| Mystery Game Puzzles (Epoch AI) | 52% | 64% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 100% |
| SAGE (Vals AI) | 51.9% | 53.6% |
| SimpleQA Verified | 70.7% | 76% |
| Terminal-Bench 4.0 (Vals AI) | 41.4% | 57.6% |
| Vending-Bench 2 (Andon Labs) | 5680.26 | 13718.16 |
| SimpleBench (SimpleBench) | 81.9% | 91.7% |
| AutomationBench | 17.4% | 51.3% |
FAQ
Is Claude Fable 5 better than Gemini 4 Argon?
Gemini 4 Argon scores 69.2 on the Respan Index (#13), ahead of Claude Fable 5 at 63.9 (#18). Gemini 4 Argon leads on 16 of the 20 benchmarks both report.
Which is cheaper, Claude Fable 5 or Gemini 4 Argon?
Claude Fable 5 lists at $10 input and $50 output per 1M tokens; Gemini 4 Argon at $2 and $10. Gemini 4 Argon is 5.0x cheaper per token at list price.