Benchmark scores
Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.
LLM Comparison
Claude Mythos/Fable 5 vs MAI-Thinking-1: benchmark scores, pricing & comparison.
Side-by-side Claude Mythos/Fable 5 vs MAI-Thinking-1 comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.
Rank #1 vs #27AskClash overall scores 93.5 vs 41.5.
Pricing $10.0/$50.0 vs —/—Input and output token prices per 1M tokens when published.
Proprietary vs ProprietaryAnthropic vs Microsoft.
Claude Mythos/Fable 5 vs MAI-Thinking-1 benchmark comparison
Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.
| Metric | Claude Mythos/Fable 5 | MAI-Thinking-1 |
|---|---|---|
| Overall Score | 93.5 | 41.5 |
| Leaderboard Rank | #1 | #27 |
| RWT | 9.5 | — |
| HLE | 64.5 | — |
| GPQA | 94.5 | 84.2 |
| IFEval | 80.3 | 85.0 |
| SWE-bench | 95.5 | 73.5 |
| SWE-Pro | 80.3 | — |
| Terminal-Bench | 88.0 | 46.0 |
| LiveCodeBench | — | 87.7 |
| OSWorld | 85.0 | — |
| Finance Agent | 56.3 | — |
| CharXiv | 93.5 | — |
| MMMU-Pro | 92.7 | — |
| Tau2 | 89.2 | — |
| Input Price (per 1M tokens) | $10.0 | — |
| Output Price (per 1M tokens) | $50.0 | — |
| Context Window | 1M+ | 256K |
| Benchmark Cells | 13 | 5 |
More Claude Mythos/Fable 5 and MAI-Thinking-1 comparisons
Explore how Claude Mythos/Fable 5 and MAI-Thinking-1 stack up against other top-ranked LLMs.
Claude Mythos/Fable 5 vs Claude Opus 4.8 (Adaptive)Claude Opus 4.8 (Adaptive) vs MAI-Thinking-1Claude Mythos/Fable 5 vs GPT-5.5 xHighGPT-5.5 xHigh vs MAI-Thinking-1Claude Mythos/Fable 5 vs GLM-5.2GLM-5.2 vs MAI-Thinking-1Claude Mythos/Fable 5 vs Claude Opus 4.7 (Adaptive)Claude Opus 4.7 (Adaptive) vs MAI-Thinking-1Claude Mythos/Fable 5 vs Qwen3.7 MaxQwen3.7 Max vs MAI-Thinking-1
How to read this comparison
Token pricing
Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.
Coverage matters
Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.
This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.