Pairwise benchmark snapshot · Aug 17, 2026noindex (thin pair)
This page compares Google: Gemini 2.5 Pro (batch) (Google) and Gemini 3.6 Pro (Google) using the latest snapshots we have as of Aug 17, 2026. Google: Gemini 2.5 Pro (batch) wins on output price at $5/1M. Gemini 3.6 Pro has the larger context window (2M tokens). Every cell below is a dated snapshot from a named public source — we do not invent missing scores, and we do not run SWE-bench ourselves.
Auto-discovered from OpenRouter (google/gemini-2.5-pro:batch). Preview until a second source matches.
Current Google Pro-class multimodal model. Long context, strong coding, billed like the 3.x Pro tier.
thinking_budgetReasoning models scale test-time compute by generating hidden chain-of-thought (CoT) tokens. These tokens are billed at standard output rates and directly expand latency (TTFT) in exchange for higher GPQA Diamond and SWE-bench Verified problem resolve rates.
Balanced reasoning for coding and multimodal comprehension.
"thinking": {
"type": "enabled",
"budget_tokens": 16384
}"reasoning": {
"effort": "medium",
"max_tokens": 2400
}Instant pairwise benchmark recalculation across 400+ LLMs
Category wins across intelligence, speed, and pricing efficiency.
Preference Elo, Coding proficiency, SWE-bench & LiveBench accuracy
Generation throughput and time to first token responsiveness
Cost per million tokens and max context window length
Each spoke is a skill. Farther from the center is better (0–100th percentile). Tap any dot to inspect details.
No shared data
No shared data
Same price
Simulate monthly production API costs in USD (US Dollar).
Google: Gemini 2.5 Pro (batch) is estimated to save $21.88/month ($263/year).
Need SWE-bench on both sides.
Lower output list price ($5/1M).
Need TTFT on both sides.
Larger window (2M).
Gemini 3.6 Pro is the side marked multimodal in the catalog.
| Target Workload | Recommended Pick | Evaluation Rationale |
|---|---|---|
| Repo / coding agents | insufficient data | Need SWE-bench on both sides. |
| High-volume chat | Google: Gemini 2.5 Pro (batch) | Lower output list price ($5/1M). |
| Voice / low-latency UI | insufficient data | Need TTFT on both sides. |
| Long-document RAG | Gemini 3.6 Pro | Larger window (2M). |
| Screenshots / vision | Gemini 3.6 Pro | Gemini 3.6 Pro is the side marked multimodal in the catalog. |
3.7 Flash vs 3.6 Pro is the current Google volume-versus-upgrade pair.
Top Anthropic vs top Google. Usually Opus 5 vs 3.6 Pro. Two different invoices.
Hub remaps to top Google vs top OpenAI Elo. Usually 3.6 Pro vs Sol. Window vs price is the plot.
2M context, Pro-class Elo and coding. Upgrade path from Flash is this page, not a vibe check.
No comments posted on this matchup yet. Be the first to share an evaluation note!
The real PNG is generated at /compare/gemini-2-5-pro-batch-vs-gemini-3-6-pro/opengraph-image for crawlers.
Verified head-to-head card
compare · Aug 13, 2026
Gemini Flash vs Pro: when Flash is the whole product
compare · Jul 24, 2026
Claude vs Gemini: coding, Elo, and output price — not a brand mashup
compare · Jul 16, 2026
Gemini vs GPT: long context versus the OpenAI flagship invoice
launch · Jul 15, 2026
Gemini 3.6 Pro: Google’s current Pro-class long-context row