Claude Fable 5 vs Gemini 4 Argon
Different efforts: max · high · Compare all at high
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models
Fable 555.5
Gemini 4 Argon57.1
Terminal-Bench 4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite
Fable 542.4
Gemini 4 Argon57.1
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation
Fable 554.1
Gemini 4 Argon77.5
Arena Text · creative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool
Fable 5 · high1,501
Gemini 4 Argon1,516
| Benchmark | Fable 5 | Gemini 4 Argon |
|---|---|---|
| Humanity's Last Exam | 55.5 | 57.1 |
| Terminal-Bench 4.0 | 42.4 | 57.1 |
| AutomationBench-AA | 54.1 | 77.5 |
| Arena Text · creative writing | 1,501 · high | 1,516 |
Specs
| Spec | Fable 5 | Gemini 4 Argon |
|---|---|---|
| Input, per 1M | $10 | !$2 |
| Output, per 1M | $50 | !$10 |
| Cost per task? | $8.75 | $1.99 |
| Speed, tok/s | 67 | 84 |
| 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.