Claude Mythos PreviewvsGPT-6.1 Sol

Claude Mythos Preview leads the overall Podium Score by 5.0 points (97.4 vs 92.4).Category wins: Claude Mythos Preview 4 — 1 GPT-6.1 Sol.Claude Mythos Preview is the cheaper pick ($15/M vs $20/M per 1M output tokens). Claude Mythos Preview is faster (80 t/s vs 75 t/s).

Claude Mythos PreviewDrag slider or hover to compareGPT-6.1 Sol
GPT-6.1 Sol
92.4
Coding: 89.0 · Speed: 75 t/s
Output Price: $20/M
Claude Mythos Preview
97.4
Coding: 80.9 · Speed: 80 t/s
Output Price: $15/M
Quick VerdictAggregated 2026 Benchmark Analysis

Claude Mythos Preview is rated higher overall with a Podium Score of 97.4 (vs 92.4 for GPT-6.1 Sol). In head-to-head domain evaluations, Claude Mythos Preview outperforms in 4 of 7 benchmark categories.

Coding & Engineering
GPT-6.1 Sol (89.0)
Inference Speed
Claude Mythos Preview (80 t/s)
Cost Efficiency
Claude Mythos Preview ($15/M)
API Price / 1M (in · out)
Claude Mythos $3/M · $15/M — GPT-6.1 Sol $5/M · $20/M

Choose Claude Mythos Preview for math and quantitative work, and GPT-6.1 Sol for coding and software engineering.

MetricClaude Mythos PreviewGPT-6.1 Sol
Podium Score97.4 ▲92.4
Arena Elo—1495
Intelligence Index—93.0
Coding80.989.0 ▲
Math100.0 ▲95.0
Reasoning98.8 ▲95.5
Agentic—86.5
Knowledge100.0 ▲89.0
Multimodal100.0 ▲93.0
Long-context—96.0
Output speed80 t/s ▲75 t/s
Output price$15/M ▲$20/M
Context window1000K1000K
0 / 4