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. | 1M | 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. | $10.00Verified organizations only | — |
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. | $50.00 | — |
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. | $0.25 | — |
| $4,500Anthropic list price | — | |
| These models have no shared benchmark scores. | ||
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. | — | 77.2% |
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% |
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. | 60.9% | — |
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. | — | 59.3% |
De novo binder design (24 hr)Protein design — de novo protein binder design within a 24-hour budget, as reported by Anthropic | 79.1% | — |
CyScenarioBenchCybersecurity — multi-step cybersecurity scenarios; each lab runs its own unique task set, so scores from different labs do not compare | 61.7% | — |
CVE RediscoveryCybersecurity — Anthropic internal evaluation: share of 1,829 published CVEs a model finds on its own from a snapshot of the project before the fix | 78.3% | — |
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. | — | 24% |
BioMysteryBench · hardBiology — Real unsolved-style biology puzzles — the AI has to reason its way to an answer the way a research biologist would. The “hard” split contains the toughest cases. Higher is better. | 44.1% | — |
BioMysteryBench · human solvedBiology — Real biology puzzles that human experts have managed to crack — can the AI reach the same answers? Higher is better. | 90.3% | — |
AIME 2026Reasoning — single-answer accuracy on the 2026 invitational mathematics exam without tools | — | 94.1% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 87.8% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 86.2% |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 78.4% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 75.8% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 82.9% |
| Overview | ||
| Company | Anthropic | Qwen |
| Release date | Sep 1 2026 | Apr 22 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Mythos 5.1vsGPT-6.2 AstraQwen3.6-27BvsGPT-6.2 AstraClaude Mythos 5.1vsGemini 4 NeonQwen3.6-27BvsGemini 4 NeonClaude Mythos 5.1vsMuse EmberQwen3.6-27BvsMuse EmberClaude Mythos 5.1vsGrok 4.7Qwen3.6-27BvsGrok 4.7Claude Mythos 5.1vsDeepSeek-V4.1-Flash-1017Qwen3.6-27BvsDeepSeek-V4.1-Flash-1017Claude Mythos 5.1vsMistral Large 4Qwen3.6-27BvsMistral Large 4Frequently asked questions
Claude Mythos 5.1 and Qwen3.6-27B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Claude Mythos 5.1 has a verified first-party price for an available API: $10.00 per million input tokens and $50.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.6-27B. Claude Mythos 5.1 requires organization verification. Qwen3.6-27B shipped 132 days before Claude Mythos 5.1, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Mythos 5.1) vs 256k (Qwen3.6-27B). Claude Mythos 5.1 is closed, while Qwen3.6-27B is open weight.
Direct benchmark comparisons are unavailable — Claude Mythos 5.1 and Qwen3.6-27B don't publish scores on any of the same benchmarks.