Gemini 3.1 ProvsGrok 4.20 Beta
Gemini 3.1 Pro | Grok 4.20 Beta | |
|---|---|---|
| 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. | 37% | 56%Best |
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. | 14.2% | — |
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. | 45.7% | — |
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. | 49.2% | — |
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. | 54.2% | — |
Coding SWE-Bench VerifiedReal 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. | 80.6% | — |
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. | 12% | — |
ML engineering MLE-BenchCan 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% | — |
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. | 75% | — |
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. | 70.3% | — |
Agentic terminal coding Terminal-Bench 2.0Can 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% | — |
Multi-step tool use MCP AtlasCan 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% | — |
General tool use ToolathlonTests how well the AI uses everyday real-world tools and apps to get things done. Higher is better. | 48.8% | — |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | 85.9% | — |
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. | 44.4% | — |
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. | 51.4% | — |
Abstract reasoning ARC-AGI-2Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 77.1%Best | 53.3% |
Advanced math FrontierMath · Tier 1–3Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | 36.9% | — |
Advanced math FrontierMath · Tier 4Very hard, research-level math problems. Tier 4 is the hardest — close to what professional research mathematicians tackle. Higher is better. | 16.7% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 94.3% | — |
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. | 76.2% | — |
Agentic financial analysis Finance Agent v2Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. | 43% | — |
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. | 1314 | — |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | 965 | — |
Knowledge work GDPval (win/tie rate)How often the AI's work matches or beats a human expert's on real knowledge-work tasks. Higher is better. | 67.3% | — |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | 83.3% | — |
Multimodal reasoning MMMU-ProA tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 80.5% | — |
Spatial reasoning Blueprint-Bench 2Can the AI reason about space and layout — for example, understanding a floor plan or blueprint? Higher is better. | 26.5% | — |
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. | 84.9% | — |
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. | 26.3% | — |
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. | 1485Best | 1475 |
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. | 1445 | — |
| Overview | ||
| Company | SpaceXAI | |
| Release date | Feb 19 2026 | Feb 17 2026 |
| Access | Proprietary | Proprietary |
Which is better: Gemini 3.1 Pro or Grok 4.20 Beta?
Gemini 3.1 Pro leads Grok 4.20 Beta on 2 of the 3 benchmarks they both report (BullshitBench v2, ARC-AGI-2, Arena Elo (Text)). Grok 4.20 Beta shipped 2 days before Gemini 3.1 Pro, 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, Grok 4.20 Beta leads at 56% vs Gemini 3.1 Pro at 37%. On ARC-AGI-2, Gemini 3.1 Pro leads at 77.1% vs Grok 4.20 Beta at 53.3%. On Arena Elo (Text), Gemini 3.1 Pro leads at 1485 vs Grok 4.20 Beta at 1475.
Frequently asked questions
Gemini 3.1 Pro was released by Google on Feb 19 2026.
Grok 4.20 Beta was released by SpaceXAI on Feb 17 2026.
Gemini 3.1 Pro leads on ARC-AGI-2 — Gemini 3.1 Pro 77.1% vs Grok 4.20 Beta 53.3%.
Other comparisons
Gemini 3.1 ProvsClaude Opus 5Grok 4.20 BetavsClaude Opus 5Gemini 3.1 ProvsGPT-5.6 SolGrok 4.20 BetavsGPT-5.6 SolGemini 3.1 ProvsMuse Spark 1.1Grok 4.20 BetavsMuse Spark 1.1Gemini 3.1 ProvsDeepSeek-V4-Flash-0731Grok 4.20 BetavsDeepSeek-V4-Flash-0731Gemini 3.1 ProvsMistral Medium 3.5Grok 4.20 BetavsMistral Medium 3.5Gemini 3.1 ProvsKimi K3Grok 4.20 BetavsKimi K3