Why CEREBRO kept it

Sol vs Opus 5.5 for coding, direct model comparison

Backlinks

Appeared in 1 briefing

• 2026-09-30

Related

Shares tags: ai/llm-mechanics · cerebro/signal

• AA's run of TerminalBench got lower scores, but similarly insane costs. 6.1 Sol now dominates the pareto frontier https://t.co/RDe1xRVJ9hx · 2026-09-30
• Looks like my numbers were better because I used Codex and AA used mini-swe-agent (think pi but shit) Might have to do my own runs of TerminalBench 4.0 on official harnesses because the difference isx · 2026-09-30
• Artificial Analysis numbers are in! GPT-6.1 Sol is performing at around Opus 5.5 Medium levels for under a third the price. Not bad at all, but still more hyped for 6.1 Astra to catch them up 👀 httpsx · 2026-09-30
• To be clear, I still think Opus 5.5 is the current GOAT for coding. GPT-6.1 Sol is a great replacement for Astra at a WAY better price, but I don't default to it for code. I absolutely default to itx · 2026-09-30
• GPT-6.1 Sol: near-Astra intelligence for a fifth of the price. It’s the most cost-efficient model for its performance available today. https://t.co/hH8PnE2Oxkx · 2026-09-30
• Updated run just finished. GPT-6.1 Sol still crushes. Turns out it performs WAY better in Codex than in mini-swe (what Artificial Analysis uses) https://t.co/nNj9JcQQvKx · 2026-09-30

Also from x.com

• AA's run of TerminalBench got lower scores, but similarly insane costs. 6.1 Sol now dominates the pareto frontier https://t.co/RDe1xRVJ9hx · 2026-09-30
• Looks like my numbers were better because I used Codex and AA used mini-swe-agent (think pi but shit) Might have to do my own runs of TerminalBench 4.0 on official harnesses because the difference isx · 2026-09-30
• Artificial Analysis numbers are in! GPT-6.1 Sol is performing at around Opus 5.5 Medium levels for under a third the price. Not bad at all, but still more hyped for 6.1 Astra to catch them up 👀 httpsx · 2026-09-30
• To be clear, I still think Opus 5.5 is the current GOAT for coding. GPT-6.1 Sol is a great replacement for Astra at a WAY better price, but I don't default to it for code. I absolutely default to itx · 2026-09-30
• GPT-6.1 Sol: near-Astra intelligence for a fifth of the price. It’s the most cost-efficient model for its performance available today. https://t.co/hH8PnE2Oxkx · 2026-09-30
• Updated run just finished. GPT-6.1 Sol still crushes. Turns out it performs WAY better in Codex than in mini-swe (what Artificial Analysis uses) https://t.co/nNj9JcQQvKx · 2026-09-30