Claude Opus 4.6vsGemini 3.1 Flash-Lite
Claude Opus 4.6 | Gemini 3.1 Flash-Lite | |
|---|---|---|
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $5.00 | $0.25 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | $25.00 | $1.50 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.50 | $0.025 |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $5.00Amazon Bedrock | — |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $25.00Amazon Bedrock | — |
| Benchmarks | ||
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 87% | 11% |
| BenchmarksPublished by one model only | ||
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 80.8% | — |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | 69% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.7% | — |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | 53% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 91.3% | — |
| Overview | ||
| Company | Anthropic | |
| Release date | Feb 5 2026 | Mar 3 2026 |
| Access | Proprietary | Proprietary |
Other comparisons
Frequently asked questions
Claude Opus 4.6 leads Gemini 3.1 Flash-Lite on 1 of the 1 benchmark they both report (BullshitBench v2). Gemini 3.1 Flash-Lite is cheaper on both input and output: $0.25 vs $5.00 per million input tokens, and $1.50 vs $25.00 per million output tokens. Claude Opus 4.6 shipped 26 days before Gemini 3.1 Flash-Lite, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On BullshitBench v2, Claude Opus 4.6 leads at 87% vs Gemini 3.1 Flash-Lite at 11%.
Claude Opus 4.6 was released by Anthropic on Feb 5 2026.
Gemini 3.1 Flash-Lite was released by Google on Mar 3 2026.
Gemini 3.1 Flash-Lite is cheaper on both input and output: $0.25 vs $5.00 per million input tokens, and $1.50 vs $25.00 per million output tokens. Rates are pay-as-you-go API prices verified on August 18, 2026.