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/35B/122B |
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% | 72% |
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% | 49.4% |
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% | 25.3% |
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% | 47.5% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 87% | 86.6% |
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. | 66.3% | 58% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 70.6% | 76.9% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 80.7% | 83.9% |
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% | — |
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. | — | 78.9% |
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% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 93.4% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 63.8% |
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% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 76.1% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 86.7% |
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. | — | 77.2% |
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 | Feb 24 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Opus 4.5vsGPT-6.2 AstraQwen3.5 MediumvsGPT-6.2 AstraClaude Opus 4.5vsGemini 4 NeonQwen3.5 MediumvsGemini 4 NeonClaude Opus 4.5vsMuse EmberQwen3.5 MediumvsMuse EmberClaude Opus 4.5vsGrok 4.7Qwen3.5 MediumvsGrok 4.7Claude Opus 4.5vsDeepSeek-V4.1-Flash-1017Qwen3.5 MediumvsDeepSeek-V4.1-Flash-1017Claude Opus 4.5vsMistral Large 4Qwen3.5 MediumvsMistral Large 4Frequently asked questions
Claude Opus 4.5 leads Qwen3.5 Medium on 5 of the 8 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 Qwen3.5 Medium. Claude Opus 4.5 shipped 92 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (Claude Opus 4.5) vs 256k (Qwen3.5 Medium). Claude Opus 4.5 is closed, while Qwen3.5 Medium is open weight.
On SWE-Bench Verified, Claude Opus 4.5 leads at 80.9% vs Qwen3.5 Medium at 72%. On Terminal-Bench 2.0, Claude Opus 4.5 leads at 59.8% vs Qwen3.5 Medium at 49.4%. On Humanity's Last Exam · no tools, Claude Opus 4.5 leads at 30.8% vs Qwen3.5 Medium at 25.3%. On Humanity's Last Exam · with tools, Qwen3.5 Medium leads at 47.5% vs Claude Opus 4.5 at 43.4%. On GPQA Diamond, Claude Opus 4.5 leads at 87% vs Qwen3.5 Medium at 86.6%. On OSWorld-Verified, Claude Opus 4.5 leads at 66.3% vs Qwen3.5 Medium at 58%. On MMMU-Pro, Qwen3.5 Medium leads at 76.9% vs Claude Opus 4.5 at 70.6%. On MMMU, Qwen3.5 Medium leads at 83.9% vs Claude Opus 4.5 at 80.7%.