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. | — | >1T |
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 | ||
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. | $15.00Amazon Bedrock | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $75.00Amazon Bedrock | — |
| $6,750Amazon Bedrock | — | |
| 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. | 74.5% | 75.3% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 80.9% | 87.4% |
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. | 43% | — |
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. | — | 85.9% |
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. | 46.5% | — |
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 | 40.9% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | — | 30.2% |
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. | — | 49.8% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 70.9% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 85.7% |
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. | 44.4% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 77.1% | — |
| Overview | ||
| Company | Anthropic | Qwen |
| Release date | Aug 5 2025 | Jan 26 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude Opus 4.1vsGPT-6.2 AstraQwen3-Max-ThinkingvsGPT-6.2 AstraClaude Opus 4.1vsGemini 4 NeonQwen3-Max-ThinkingvsGemini 4 NeonClaude Opus 4.1vsMuse EmberQwen3-Max-ThinkingvsMuse EmberClaude Opus 4.1vsGrok 4.7Qwen3-Max-ThinkingvsGrok 4.7Claude Opus 4.1vsDeepSeek-V4.1-Flash-1017Qwen3-Max-ThinkingvsDeepSeek-V4.1-Flash-1017Claude Opus 4.1vsMistral Large 4Qwen3-Max-ThinkingvsMistral Large 4Frequently asked questions
Qwen3-Max-Thinking leads Claude Opus 4.1 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). Claude Opus 4.1 shipped 174 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (Claude Opus 4.1) vs 256k (Qwen3-Max-Thinking).
On SWE-Bench Verified, Qwen3-Max-Thinking leads at 75.3% vs Claude Opus 4.1 at 74.5%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs Claude Opus 4.1 at 80.9%.