Claude Fable 5 (Max, Opus 4.8 Fallback) vs gpt-oss-20b (High)
Which is better for the money: Claude Fable 5 (Max, Opus 4.8 Fallback) by Anthropic or gpt-oss-20b (High) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
Claude Fable 5 (Max, Opus 4.8 Fallback) scores 40.6 points higher (49.6 vs 9.0) but costs 387× as much to run the benchmark ($11161 vs $28.8; flagship vs budget cost classes). They are not alternatives at one budget: pick Claude Fable 5 (Max, Opus 4.8 Fallback) when you need intelligence above 9.0, and gpt-oss-20b (High) when 9.0 is enough.
| Metric | Claude Fable 5 (Max, Opus 4.8 Fallback) | gpt-oss-20b (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 49.6 | 9.0 | −81.9% gpt-oss-20b (High) is 81.9% less intelligent |
| Total AA cost (lower is better) | $11,160.86 | $28.81 | −99.7% gpt-oss-20b (High) is 99.7% cheaper |
| End-to-end time (lower is better) | 85.62s | 15.23s | −82.2% gpt-oss-20b (High) is 82.2% faster |
| Price per 1M tokens (in / out) | $10.0 / $50.0 | $0.05 / $0.22 | |
| Input modalities | Text, Image | Text |
gpt-oss-20b (High) vs Claude Fable 5 (Max, Opus 4.8 Fallback): 81.9% less intelligence, 99.7% less cost to run the AA benchmark, and 82.2% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Fable 5 (Max, Opus 4.8 Fallback) is off the frontier: at the same or lower cost, Claude Opus 5.5 (Max, Default Fallback) scores 57.60 for $8708.
- gpt-oss-20b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
Claude Fable 5 (Max, Opus 4.8 Fallback)gpt-oss-20b (High)Today's Pareto frontierOpen-weights frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-fable-5/gpt-oss-20b · Markdown: /api/v1/compare/claude-fable-5/gpt-oss-20b?format=md · llms.txt · agent skill