Claude Opus 4.8vsGemini 3.7 Flash
Claude Opus 4.8 | Gemini 3.7 Flash | |
|---|---|---|
| Specifications | ||
Context window | 1M | 1M |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given 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. | 95% | — |
Prompt injection robustness Gray Swan IPI · k = 1Attackers 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. | 0.5% | — |
Prompt injection robustness Gray Swan IPI · k = 10Attackers 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. | 4.1% | — |
Prompt injection robustness Gray Swan IPI · k = 15Attackers 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. | 5.5% | — |
Agentic coding SWE-Bench ProCan 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. | 69.2% | — |
Multilingual coding SWE-Bench MultilingualLike SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 84.4% | — |
Agentic coding CursorBench v3.2Cursor's own test of harder, real-world coding tasks inside a code editor, on the refreshed v3.2 task set. Scores aren't comparable with v3.1. Higher is better. | 62.3% | — |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | 63.8% | — |
Agentic coding DeepSWE 1.1Artificial 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. | — | 65.3% |
Agentic coding DeepSWE 1.0Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. Higher is better. | 55.8% | — |
Agentic coding FrontierCode v1.1 (Main) · main splitA 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. | — | 43.6% |
Next.js coding Next.js EvalsVercel'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. | 88% | — |
Agentic computer work Frontier-Bench v0.1A 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. | 21.1% | — |
Agentic terminal coding Terminal-Bench 3.0command-line task completion (v3.0, much harder task set) | — | 14.9% |
Agentic terminal coding Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 74.6% | 85.8%Best |
Browser agent BU BenchCan the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | 74% | — |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | 84.3% | — |
Multidisciplinary reasoning Humanity's Last Exam · no toolsHumanity'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. | 49.8% | — |
Multidisciplinary reasoning Humanity's Last Exam · with toolsHumanity'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. | 57.9% | — |
Multidisciplinary reasoning Humanity's Last Exam (Verified)The re-checked edition of Humanity's Last Exam: the same extremely hard expert questions, minus the ones found to be flawed or wrongly answered. Scores on it run lower than on the original exam, so read the two as separate tests rather than a before-and-after. Higher is better. | — | 53.6% |
Biology BioMysteryBench · hardReal 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. | — | 43.5% |
Biology BioMysteryBench · human solvedReal biology puzzles that human experts have managed to crack — can the AI reach the same answers? Higher is better. | — | 87.1% |
Biology LAB-Bench 2Everyday tasks from a working biology lab — reading protocols, interpreting figures and sequence data, and answering the practical questions a researcher hits at the bench. Higher is better. | — | 82.1% |
Agentic computer use OSWorld 2.0Can 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. | — | 38.1% |
Agentic computer use OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 83.4% | — |
Agentic computer use Agent's Last ExamA hard set of desktop and operating-system tasks an AI agent has to finish by looking at the screen and working the machine itself. The score is the share it passes outright — partial credit does not count. Higher is better. | — | 26.3% |
Business workflows AutomationBenchTests 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. | — | 30.4% |
Agentic financial analysis Finance Agent v2Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. | 53.9% | — |
Agentic legal work Harvey's Legal Agent BenchmarkHarvey's test of whether an AI agent can complete real legal work — drafting and reviewing documents, working with spreadsheets and presentations, and navigating files the way a lawyer's assistant would. Higher is better. | 9.58% | 90.7%Best |
Tax questions TaxEval v2A set of real tax questions created by Vals AI — can the AI give accurate answers about tax rules and filings? Higher is better. | 75.63% | — |
Medical admin work MedScribeCan the AI support doctors with their administrative work, like notes and paperwork? Created by Vals AI. Higher is better. | 85.75% | — |
Overall intelligence AA Intelligence IndexArtificial Analysis composite intelligence index across evals | — | 56 |
Knowledge work GDPval-AAMeasures how well the AI does economically valuable knowledge work, judged against human experts. Shown as a rating (like a chess Elo) — higher is better. | 1890 | — |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | 1600Best | 1525 |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 84.5% |
Document comprehension GDP.PDFReal professional PDFs — filings, reports, technical documents — with questions an expert in that field would ask. Tests whether the AI reads the page as a document, layout and figures included, rather than as loose text. Higher is better. | — | 34% |
Video understanding LVBenchCan the AI follow a very long video — up to an hour — and answer questions that need details from far apart in it? Higher is better. | — | 85.4% |
Long context MRCR v2 (8-needle) · 128k averageTests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better. | — | 97% |
Long context MRCR v2 (8-needle) · 1M pointwiseTests whether the AI can find specific details buried inside an enormous document (around 1 million tokens — many books). Higher is better. | — | 62.5% |
Community preference Arena Elo (Text)Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | 1482 | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | 1568 | 1588Best |
| Overview | ||
| Company | Anthropic | |
| Release date | May 28 2026 | Aug 13 2026 |
| Access | Proprietary | Proprietary |
Which is better: Claude Opus 4.8 or Gemini 3.7 Flash?
Gemini 3.7 Flash leads Claude Opus 4.8 on 3 of the 4 benchmarks they both report (Terminal-Bench 2.1, Harvey's Legal Agent Benchmark, GDPval-AA v2, Arena Elo (Code)). Claude Opus 4.8 shipped 77 days before Gemini 3.7 Flash, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Opus 4.8) vs 1M (Gemini 3.7 Flash).
On Terminal-Bench 2.1, Gemini 3.7 Flash leads at 85.8% vs Claude Opus 4.8 at 74.6%. On Harvey's Legal Agent Benchmark, Gemini 3.7 Flash leads at 90.7% vs Claude Opus 4.8 at 9.58%. On GDPval-AA v2, Claude Opus 4.8 leads at 1600 vs Gemini 3.7 Flash at 1525. On Arena Elo (Code), Gemini 3.7 Flash leads at 1588 vs Claude Opus 4.8 at 1568.
Frequently asked questions
Claude Opus 4.8 was released by Anthropic on May 28 2026.
Gemini 3.7 Flash was released by Google on Aug 13 2026.
Gemini 3.7 Flash leads on Terminal-Bench 2.1 — Claude Opus 4.8 74.6% vs Gemini 3.7 Flash 85.8%.
Claude Opus 4.8 has a 1M context window; Gemini 3.7 Flash has 1M.
Other comparisons
Claude Opus 4.8vsGPT-5.6-CyberGemini 3.7 FlashvsGPT-5.6-CyberClaude Opus 4.8vsMuse GlimmerGemini 3.7 FlashvsMuse GlimmerClaude Opus 4.8vsGrok 4.6Gemini 3.7 FlashvsGrok 4.6Claude Opus 4.8vsDeepSeek-V4-Pro-0813Gemini 3.7 FlashvsDeepSeek-V4-Pro-0813Claude Opus 4.8vsMistral Medium 3.5Gemini 3.7 FlashvsMistral Medium 3.5Claude Opus 4.8vsKimi K3Gemini 3.7 FlashvsKimi K3