Claude Mythos PreviewvsGemini 3.1 Flash-Lite Preview
Claude Mythos Preview leads the overall Podium Score by 12.0 points (97.4 vs 85.4).Category wins: Claude Mythos Preview 5 — 0 Gemini 3.1 Flash-Lite Preview.Gemini 3.1 Flash-Lite Preview is the cheaper pick ($0.3/M vs $15/M per 1M output tokens). Gemini 3.1 Flash-Lite Preview is faster (210 t/s vs 80 t/s).
Claude Mythos PreviewDrag slider or hover to compareGemini 3.1 Flash-Lite Preview
Quick VerdictAggregated 2026 Benchmark Analysis
Claude Mythos Preview is rated higher overall with a Podium Score of 97.4 (vs 85.4 for Gemini 3.1 Flash-Lite Preview). In head-to-head domain evaluations, Claude Mythos Preview outperforms in 5 of 7 benchmark categories.
Coding & Engineering
Claude Mythos Preview (80.9)
Inference Speed
Gemini 3.1 Flash-Lite Preview (210 t/s)
Cost Efficiency
Gemini 3.1 Flash-Lite Preview ($0.3/M)
API Price / 1M (in · out)
Claude Mythos $3/M · $15/M — Gemini 3.1 Flash-Lite $0.075/M · $0.3/M
Choose Claude Mythos Preview for math and quantitative work, and Gemini 3.1 Flash-Lite Preview for cost-sensitive workloads.
| Metric | Claude Mythos Preview | Gemini 3.1 Flash-Lite Preview |
|---|---|---|
| Podium Score | 97.4 ▲ | 85.4 |
| Arena Elo | — | 1365 |
| Intelligence Index | — | 85.0 |
| Coding | 80.9 ▲ | 76.0 |
| Math | 100.0 ▲ | 80.0 |
| Reasoning | 98.8 ▲ | 82.0 |
| Agentic | — | 74.0 |
| Knowledge | 100.0 ▲ | 81.0 |
| Multimodal | 100.0 ▲ | 89.0 |
| Long-context | — | 94.0 |
| Output speed | 80 t/s | 210 t/s ▲ |
| Output price | $15/M | $0.3/M ▲ |
| Context window | 1000K | 1000K |
Scores aggregated from five independent leaderboards. See Methodology. More head-to-heads: Claude Mythos vs Claude 5.5 Sonnet · Claude Mythos vs Kimi K3.1 Pro · Claude Mythos vs Eleven Multilingual v3 · Claude Mythos vs FLUX.2 Pro