AI model matchup

Claude Mythos Preview vs GPT-6 Sol

A side-by-side look at published capability scores, listed API pricing, speed, context, and license - to help you decide which trade-offs fit your work.

OpenAI

GPT-5.6 Sol

Rank #1 • Score 57.2
Comparison Metrics
Speed: 89c/s vs 68c/s
Pricing: $7.78 vs $7.22
Anthropic

Claude Opus 5

Rank #2 • Score 56.2

Claude Mythos PreviewvsGPT-6 Sol

GPT-6 Sol leads the RankLLMs Index by 2.3 points (60.5 vs 58.2). Verified API Pricing: $0.00 (Claude Mythos Preview) vs $2.00 (GPT-6 Sol) per 1M tokens.

Capability profile

Claude Mythos PreviewGPT-6 Sol

Speed duel

tps
Claude Mythos Preview50
GPT-6 Sol126

Price duel

$/1M
Claude Mythos Preview$0.00
GPT-6 Sol$2.00

Shorter bar = cheaper. Blended per 1M tokens.

MetricClaude Mythos PreviewGPT-6 Sol
RankLLMs Overall Score58.2 pts 60.5 pts ▲
Reasoning65.8 78.5 ▲
Coding82.2 84.8 ▲
Agentic Tool Use85.4 ▲65.2
Code Arena Elo1743 1950 ▲
Inference Speed50 tps 126 tps ▲
API Price (per 1M tokens)$0.00 ▲$2.00
Context Window1M 1.1M
LicenseProprietary Proprietary
Global Rank#6 #5 ▲

Decision notes

What the numbers suggest

GPT-6 Sol leads the RankLLMs overall score by 2.3 points. Claude Mythos Preview has the lower listed API rate ($0.00 per 1M tokens).

Treat the overall index as a starting point, then prioritize the benchmark that resembles your task. Published scores and provider pricing can change; this comparison does not represent a first-party test of either model.

Overall index
GPT-6 Sol leads
58.2 to 60.5 pts
Coding score
GPT-6 Sol leads
82.2 to 84.8 pts
Reasoning score
GPT-6 Sol leads
65.8 to 78.5 pts
Agentic score
Claude Mythos Preview leads
85.4 to 65.2 pts

Choose by workload

Which profile fits your use?

Anthropic

Consider Claude Mythos Preview when

your workload gives more weight to the lower listed API rate. Compare those signals with your own task mix, latency needs, and budget.

View Claude Mythos Preview profile

OpenAI

Consider GPT-6 Sol when

your workload gives more weight to the higher listed coding score, the higher listed reasoning score, the higher overall index score. Compare those signals with your own task mix, latency needs, and budget.

View GPT-6 Sol profile

Compare a different pairRead editorial comparisons