Claude Fable 5 vs Gemini 4 Argon
EBR Bench?
Fable 539.5
Gemini 4 Argon64.8
Harvey LAB-AA 1.1?
Fable 5—
Gemini 4 Argon3.9
| Benchmark | Fable 5 | Gemini 4 Argon |
|---|---|---|
| AutomationBench-AA | 54.1 | 77.5 |
| GDPval-AA (work tasks) 2.1 | 1,609.9 | 1,631.1 |
| AA Analyst Agent | 48.8 | 48.8 |
| Terminal-Bench 4.0 | 42.4 | 57.1 |
| AA-Briefcase 1.1 · Elo | 1,536.9 | 1,483.3 |
| AA-LCR (long context) 1.1 | 82.3 | 79.7 |
| EBR Bench | 39.5 | 64.8 |
| Furniture Assembly | 35.8 | 72.5 |
| AutomationBench · Zapier run | — | 51.3 |
| τ³-bench · banking · 1.0.1 | 39.7 | — |
| τ³-Banking · AA | 38.1 | — |
| Terminal-Bench Hard (version unstated) | 62.9 | — |
| Terminal-Bench Science 0.1 | — | 52.9 |
| DeepSWE 1.1 | 69.7 | — |
| EnterpriseOps-Gym-AA | 51.1 | — |
| FrontierCode 1.1 | — | 43.5 |
| Harvey LAB-AA 1.1 | — | 3.9 |
| SWE-bench Pro (v2 full) | — | 99.2 |
| SWE-bench Pro (v2 hard) | — | 92.2 |
Specs
| Spec | Fable 5 | Gemini 4 Argon |
|---|---|---|
| Input, per 1M | $10 | !$2 |
| Output, per 1M | $50 | !$10 |
| Cost per task? | $8.75 | $1.62 |
| Speed, tok/s | 67 | 79 |
| Context | 1M | 1M |
| Weights | Closed | Closed |
| Released | Jun 2026 | Oct 2026 |
| See images | ✓ | ✓ |
| Read PDFs | Partial | ✓ |
| Hear audio | — | ✓ |
| Watch video | — | ✓ |
| Call tools | ✓ | ✓ |
| Force a tool call | Partial | Partial |
| Return strict JSON | ✓ | ✓ |
| Search the web | ? | ✓ |
| Run code | ? | ✓ |
| Use a computer | ? | ? |
What breaks when you switch
Fable 5 → Gemini 4 Argon
Synchronous output stops at 65,536›
With background false, output limits above 65,536 tokens return HTTP 400; stay at or below that limit.
Sampling parameters are ignored›
temperature, top_p and top_k are ignored; remove them from requests.
No explicit caching›
Explicit caching is unavailable; omit explicit cache requests.
Gemini 4 Argon → Fable 5
Nothing known.