Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | — | 27B |
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. | 200k | 256k |
| 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 | — |
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 | — |
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 | — |
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. | $5.00Amazon Bedrock | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $25.00Amazon Bedrock | — |
| $2,250Anthropic list price | — | |
| Benchmarks | ||
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. | 80.9% | 77.2% |
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. | 59.8% | 59.3% |
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. | 30.8% | 24% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 87% | 87.8% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 70.6% | 75.8% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 80.7% | 82.9% |
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. | 90% | — |
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. | — | 71.3% |
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. | — | 36.2% |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | — | 83.9% |
MCP Atlas · original harnessMulti-step tool use — pass rate under the original tool-use harness, before Scale changed the judge and retry handling in April 2026 | 62.3% | — |
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. | 43.4% | — |
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. | 37.64% | — |
AIME 2026Reasoning — single-answer accuracy on the 2026 invitational mathematics exam without tools | — | 94.1% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 86.2% |
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. | 66.3% | — |
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. | 1416 | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 78.4% |
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. | 1138 | — |
| Overview | ||
| Company | Anthropic | Qwen |
| Release date | Nov 24 2025 | Apr 22 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Opus 4.5vsGPT-6.2 AstraQwen3.6-27BvsGPT-6.2 AstraClaude Opus 4.5vsGemini 4 NeonQwen3.6-27BvsGemini 4 NeonClaude Opus 4.5vsMuse EmberQwen3.6-27BvsMuse EmberClaude Opus 4.5vsGrok 4.7Qwen3.6-27BvsGrok 4.7Claude Opus 4.5vsDeepSeek-V4.1-Flash-1017Qwen3.6-27BvsDeepSeek-V4.1-Flash-1017Claude Opus 4.5vsMistral Large 4Qwen3.6-27BvsMistral Large 4Frequently asked questions
Claude Opus 4.5 and Qwen3.6-27B are evenly matched across the 6 benchmarks they both report. Only Claude Opus 4.5 has a verified first-party price for an available API: $5.00 per million input tokens and $25.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.6-27B. Claude Opus 4.5 shipped 149 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (Claude Opus 4.5) vs 256k (Qwen3.6-27B). Claude Opus 4.5 is closed, while Qwen3.6-27B is open weight.
On SWE-Bench Verified, Claude Opus 4.5 leads at 80.9% vs Qwen3.6-27B at 77.2%. On Terminal-Bench 2.0, Claude Opus 4.5 leads at 59.8% vs Qwen3.6-27B at 59.3%. On Humanity's Last Exam · no tools, Claude Opus 4.5 leads at 30.8% vs Qwen3.6-27B at 24%. On GPQA Diamond, Qwen3.6-27B leads at 87.8% vs Claude Opus 4.5 at 87%. On MMMU-Pro, Qwen3.6-27B leads at 75.8% vs Claude Opus 4.5 at 70.6%. On MMMU, Qwen3.6-27B leads at 82.9% vs Claude Opus 4.5 at 80.7%.