Compare AI models
| Specifications | ||
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 1M | 1M |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $0.006Relace |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.30Alibaba |
| — | $24.40Morph · fp8 | |
| Benchmarks | ||
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 83.1% | 88.1% |
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. | 56.8% | 36.8% |
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% | 63.9% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 94.5% | 90.9% |
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. | — | 57% |
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. | 77.8% | — |
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. | 93.9% | — |
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. | 87.3% | — |
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% | — |
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. | — | 74.2% |
NL2Repo-BenchRepo-level code generation — Tests whether the AI can turn a natural-language requirement into working code across an entire repository, not just produce a single function or patch. Higher is better. | — | 65.4% |
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. | — | 31.2% |
Terminal-Bench 3.0Agentic terminal coding — command-line task completion (v3.0, much harder task set) | — | 30% |
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. | — | 90.6% |
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. | 82% | — |
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. | 79.6% | — |
Agent's Last Exam · pass@1Agentic computer use — A 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. | — | 31.8% |
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. | — | 54.8% |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 86.1% | — |
CharXiv Reasoning · with toolsChart reasoning — The same chart-and-figure reasoning test, run with the AI allowed to use tools — writing code to inspect the image, for instance — rather than reading the chart unaided. Scores run higher than the unaided version, so read the two as separate tests. Higher is better. | 93.2% | — |
Chartography · with toolsChart tasks — A chart-centred test run with tools available to the AI, reported separately from the chart-reading benchmarks above it. Higher is better. | — | 78.9% |
GraphWalks BFS (256K–1M)Long context — breadth-first search F1 on the 200 GraphWalks problems with 256K to 1M tokens of context | 80% | — |
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. | — | 1634 |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Apr 7 2026 | Sep 10 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Mythos PreviewvsGPT-6.1 TerraDeepSeek-V4.1-FlashvsGPT-6.1 TerraClaude Mythos PreviewvsGemini 4 CarbonDeepSeek-V4.1-FlashvsGemini 4 CarbonClaude Mythos PreviewvsMuse EmberDeepSeek-V4.1-FlashvsMuse EmberClaude Mythos PreviewvsGrok 4.7DeepSeek-V4.1-FlashvsGrok 4.7Claude Mythos PreviewvsMistral Large 4DeepSeek-V4.1-FlashvsMistral Large 4Claude Mythos PreviewvsKimi K3.1 ProDeepSeek-V4.1-FlashvsKimi K3.1 ProFrequently asked questions
Claude Mythos Preview leads DeepSeek-V4.1-Flash on 3 of the 4 benchmarks they both report (CyberGym, Humanity's Last Exam, GPQA Diamond). Claude Mythos Preview shipped 156 days before DeepSeek-V4.1-Flash, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Mythos Preview) vs 1M (DeepSeek-V4.1-Flash). Claude Mythos Preview is closed, while DeepSeek-V4.1-Flash is open weight.
On CyberGym, DeepSeek-V4.1-Flash leads at 88.1% vs Claude Mythos Preview at 83.1%. On Humanity's Last Exam · no tools, Claude Mythos Preview leads at 56.8% vs DeepSeek-V4.1-Flash at 36.8%. On Humanity's Last Exam · with tools, Claude Mythos Preview leads at 64.7% vs DeepSeek-V4.1-Flash at 63.9%. On GPQA Diamond, Claude Mythos Preview leads at 94.5% vs DeepSeek-V4.1-Flash at 90.9%.