Claude Mythos PreviewvsGPT-Image 2
Claude Mythos Preview leads the overall Podium Score by 4.3 points (97.4 vs 93.1).Category wins: Claude Mythos Preview 5 — 0 GPT-Image 2.GPT-Image 2 is the cheaper pick ($0.09/M vs $15/M per 1M output tokens). Claude Mythos Preview is faster (80 t/s vs 25 t/s).
Claude Mythos PreviewDrag slider or hover to compareGPT-Image 2
Quick VerdictAggregated 2026 Benchmark Analysis
Claude Mythos Preview is rated higher overall with a Podium Score of 97.4 (vs 93.1 for GPT-Image 2). 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
Claude Mythos Preview (80 t/s)
Cost Efficiency
GPT-Image 2 ($0.09/M)
API Price / 1M (in · out)
Claude Mythos $3/M · $15/M — GPT-Image 2 $0.09/M · $0.09/M
Choose Claude Mythos Preview for math and quantitative work, and GPT-Image 2 for cost-sensitive workloads.
| Metric | Claude Mythos Preview | GPT-Image 2 |
|---|---|---|
| Podium Score | 97.4 ▲ | 93.1 |
| Arena Elo | — | 1470 |
| Intelligence Index | — | 93.0 |
| Coding | 80.9 ▲ | 0.0 |
| Math | 100.0 ▲ | 0.0 |
| Reasoning | 98.8 ▲ | 55.0 |
| Agentic | — | 30.0 |
| Knowledge | 100.0 ▲ | 70.0 |
| Multimodal | 100.0 ▲ | 99.2 |
| Long-context | — | 60.0 |
| Output speed | 80 t/s ▲ | 25 t/s |
| Output price | $15/M | $0.09/M ▲ |
| Context window | 1000K ▲ | 128K |
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