Gemini 3.6 Flash comparison chart shows new pricing and benchmark gains
bdsqlsz · x · 2026-07-21
A comparison image claims Gemini 3.6 Flash has arrived and immediately changed the perceived lineup enough that a Codex reset was postponed.
The chart compares pricing and benchmark results across several models, including Gemini 3.6 Flash, Gemini 3.5 Flash, Gemini 3.1 Pro, GPT-5.6 Luna, Grok 4.5, and Claude Sonnet 5.
- Pricing: Gemini 3.6 Flash is shown at $1.50 / $7.50 per 1M tokens for input/output, undercutting some rivals on output price.
- Benchmarks: The image claims strong results on SWE-Bench Pro, DeepSWE, Terminal-bench, MLE-Bench, GDPVal-AA V2, OSWorld-Verified, CharXiv Reasoning, and GDM-MRCR v2.
- The post itself is a short reaction rather than a full launch announcement, but the attached benchmark table is the substantive part.
Related event: Google Launches Three New Gemini Models, Announces Gemini 4 Pre-training(157 posts)→
More from Models
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11
- Terminal Bench v4: GLM-5.3 Leads at 41.9%, Kimi-K3 Underwhelms at 12.6% — Ok_Warning2146 · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11