Claude Opus 5vsGemini 3.1 Pro
Claude Opus 5 | Gemini 3.1 Pro | |
|---|---|---|
| Specifications | ||
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | 1M | — |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $5.00 | $2.00 |
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 | $12.00 |
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 | $0.20 |
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. | 73% | 37% |
Gray Swan IPI · k = 1Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better. | 0.2% | 14.2% |
Gray Swan IPI · k = 10Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 10 tries and counts an attack as successful if any of them works. Lower is better. | 1.6% | 45.7% |
Gray Swan IPI · k = 15Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 15 tries and counts an attack as successful if any of them works. Lower is better. | 2% | 49.2% |
ProgramBenchProgram reconstruction — The AI receives a working program and its documentation, then builds a replacement from scratch without the original source code, internet access or decompilation. The score is the percentage of 200 programs that pass every behavioral test. We record each model's best published mini-SWE-agent result, including higher reasoning efforts where available. Partial test-pass rates and almost-solved programs do not count toward this score. Equal scores share a rank here; the official board also uses partial progress to break ties. Higher is better. | 4.5% | 0% |
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | 79.2% | 54.2% |
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. | 96% | 80.6% |
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | 68.8% | 12% |
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. | 94% | 58% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 90.8% | 85.9% |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | 56.3% | 44.4% |
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. | 64.7% | 51.4% |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 90.4% | 77.1% |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | 1861 | 965 |
| BenchmarksPublished by one model only | ||
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 89.5% | — |
SWE-Bench MultimodalMultimodal coding — Real bug reports that arrive with pictures attached — a screenshot, a mockup, a page rendering wrongly — so the AI has to read the image as well as the code to work out what to fix. Higher is better. | 59.4% | — |
FrontierCode v1.1 (Main) · main splitAgentic coding — A set of very hard, frontier-difficulty coding tasks an AI agent has to complete end to end. The score is the share of tasks in the main split it solves. Higher is better. | 53.4% | — |
MLE-BenchML engineering — Can the AI do the work of a machine-learning engineer? It competes in real Kaggle competitions — building, training, and tuning models end to end — and the score reflects how well it places. Higher is better. | — | 42.6% |
Supabase Evals · with skillsSupabase coding — Supabase's own open benchmark: a coding agent is dropped into a real Supabase project and asked to do real work — set up a schema, fix a broken security policy, debug an Edge Function — and every run is checked against a live Supabase stack. This is the headline number, where the agent has Supabase's own skills loaded, as most people building on Supabase would. The score is the share of scenarios it got right. Higher is better. | 91.3% | — |
Supabase Evals · no skillsSupabase coding — The same Supabase scenarios, but with none of Supabase's skills loaded — so it measures what the model already knows about building on Supabase, rather than how well it follows Supabase's supplied instructions. Higher is better. | 89.9% | — |
Frontier-Bench v0.1Agentic computer work — A hard, ever-evolving set of real computer tasks — coding, system administration, data work, and more — that an AI agent has to complete on its own. Run by the Harbor / Laude Institute team as the successor to Terminal-Bench (v0.1 is the first release of the task set). The score is the share of tasks solved. Higher is better. | 43.3% | — |
Terminal-Bench 4.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better. | 51.82% | — |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 70.3% |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 68.5% |
Terminal-Bench-Science 0.1Agentic scientific computing — The same command-line setup as Terminal-Bench, pointed at scientific work: the AI has to drive research tooling and computational workflows through to a result, rather than administer a machine. Version 0.1 is the first release of the task set, and scores run lower than on the general board. Higher is better. | 29% | — |
MCP AtlasMulti-step tool use — Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | — | 78.2% |
ToolathlonGeneral tool use — Tests how well the AI uses everyday real-world tools and apps to get things done. Higher is better. | — | 48.8% |
ARC-AGI-3Novel problem-solving — The third generation of the ARC-AGI series: instead of static puzzles, the AI is dropped into small interactive game-like environments it has never seen and has to figure out the rules and solve them on its own. Higher is better. | 30.2% | — |
FrontierMath · Tier 1–3Advanced math — Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | — | 36.9% |
FrontierMath · Tier 4Advanced math — Very hard, research-level math problems. Tier 4 is the hardest — close to what professional research mathematicians tackle. Higher is better. | — | 16.7% |
BioMysteryBench · hardBiology — Real unsolved-style biology puzzles — the AI has to reason its way to an answer the way a research biologist would. The “hard” split contains the toughest cases. Higher is better. | 49.4% | — |
BioMysteryBench · human solvedBiology — Real biology puzzles that human experts have managed to crack — can the AI reach the same answers? Higher is better. | 90.1% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 94.3% |
OSWorld 2.0Agentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.0 is a harder, refreshed task set. Higher is better. | 70.6% | — |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | — | 76.2% |
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. | 26% | — |
Finance Agent v2Agentic financial analysis — Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. | — | 43% |
Harvey's Legal Agent Benchmark (Held-out)Agentic legal work — Harvey's test of whether an AI agent can complete real legal work, scored on a held-out set of tasks the model makers never see — making the numbers harder to game. Higher is better. | 11.7% | — |
HealthBench ProfessionalHealth — Realistic health conversations graded against detailed rubrics written by physicians — can the AI respond the way a careful medical professional would? Higher is better. | 59.8% | — |
GDPval-AAKnowledge work — Measures how well the AI does economically valuable knowledge work, judged against human experts. Shown as a rating (like a chess Elo) — higher is better. | — | 1314 |
AA-BriefcaseKnowledge work — Artificial Analysis agentic office-work eval (Elo) | 1685 | — |
GDPval (win/tie rate)Knowledge work — How often the AI's work matches or beats a human expert's on real knowledge-work tasks. Higher is better. | — | 67.3% |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 83.3% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 80.5% |
Blueprint-Bench 2Spatial reasoning — Can the AI reason about space and layout — for example, understanding a floor plan or blueprint? Higher is better. | — | 26.5% |
MRCR v2 (8-needle) · 128k averageLong context — Tests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better. | — | 84.9% |
MRCR v2 (8-needle) · 1M pointwiseLong context — Tests whether the AI can find specific details buried inside an enormous document (around 1 million tokens — many books). Higher is better. | — | 26.3% |
threejsevalCommunity preference (Three.js) — Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better. | 1770 | — |
| Overview | ||
| Company | Anthropic | |
| Release date | Jul 24 2026 | Feb 19 2026 |
| Access | Proprietary | Proprietary |
Other comparisons
Claude Opus 5vsGPT-6 AstraGemini 3.1 ProvsGPT-6 AstraClaude Opus 5vsMuse Spark 1.3Gemini 3.1 ProvsMuse Spark 1.3Claude Opus 5vsGrok 4.6Gemini 3.1 ProvsGrok 4.6Claude Opus 5vsDeepSeek-V4.1-FlashGemini 3.1 ProvsDeepSeek-V4.1-FlashClaude Opus 5vsMistral Medium 3.5Gemini 3.1 ProvsMistral Medium 3.5Claude Opus 5vsKimi K3Gemini 3.1 ProvsKimi K3
Frequently asked questions
Claude Opus 5 leads Gemini 3.1 Pro on 14 of the 14 benchmarks they both report. Gemini 3.1 Pro is cheaper on both input and output: $2.00 vs $5.00 per million input tokens, and $12.00 vs $25.00 per million output tokens. Figures are base-tier rates. Gemini 3.1 Pro shipped 155 days before Claude Opus 5, 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 5 leads at 73% vs Gemini 3.1 Pro at 37%. On Gray Swan IPI · k = 1, Claude Opus 5 leads at 0.2% vs Gemini 3.1 Pro at 14.2%. On Gray Swan IPI · k = 10, Claude Opus 5 leads at 1.6% vs Gemini 3.1 Pro at 45.7%. On Gray Swan IPI · k = 15, Claude Opus 5 leads at 2% vs Gemini 3.1 Pro at 49.2%. On ProgramBench, Claude Opus 5 leads at 4.5% vs Gemini 3.1 Pro at 0%. On SWE-Bench Pro, Claude Opus 5 leads at 79.2% vs Gemini 3.1 Pro at 54.2%. On SWE-Bench Verified, Claude Opus 5 leads at 96% vs Gemini 3.1 Pro at 80.6%. On DeepSWE 1.1, Claude Opus 5 leads at 68.8% vs Gemini 3.1 Pro at 12%. On Next.js Evals, Claude Opus 5 leads at 94% vs Gemini 3.1 Pro at 58%. On BrowseComp, Claude Opus 5 leads at 90.8% vs Gemini 3.1 Pro at 85.9%. On Humanity's Last Exam · no tools, Claude Opus 5 leads at 56.3% vs Gemini 3.1 Pro at 44.4%. On Humanity's Last Exam · with tools, Claude Opus 5 leads at 64.7% vs Gemini 3.1 Pro at 51.4%. On ARC-AGI-2, Claude Opus 5 leads at 90.4% vs Gemini 3.1 Pro at 77.1%. On GDPval-AA v2, Claude Opus 5 leads at 1861 vs Gemini 3.1 Pro at 965.