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. | 256k | — |
| Benchmarks | ||
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% | 79.8% |
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% | 69.3% |
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. | — | 54% |
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% | — |
CursorBench 4.0Agentic coding — Cursor's own test of coding agents on ambiguous, multi-file tasks taken from real Cursor sessions — editing, refactoring, investigating a codebase, understanding what the user meant, managing jobs and following a design. Cursor runs each model at several reasoning efforts; each release here carries the score of its best listed effort. Scores aren't comparable with earlier CursorBench versions. Higher is better. | — | 27.7% |
DeepSWE 1.0Agentic 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. Higher is better. | — | 18% |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | — | 82% |
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 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. | — | 73% |
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% | — |
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% | — |
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. | — | 1083 |
| Overview | ||
| Company | Qwen | SpaceXSI |
| Release date | Apr 22 2026 | May 18 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Qwen3.6-27BvsClaude Fable 5.2Composer 2.5vsClaude Fable 5.2Qwen3.6-27BvsGPT-6.2 AstraComposer 2.5vsGPT-6.2 AstraQwen3.6-27BvsGemini 4 NeonComposer 2.5vsGemini 4 NeonQwen3.6-27BvsMuse EmberComposer 2.5vsMuse EmberQwen3.6-27BvsDeepSeek-V4.1-Flash-1017Composer 2.5vsDeepSeek-V4.1-Flash-1017Qwen3.6-27BvsMistral Large 4Composer 2.5vsMistral Large 4Frequently asked questions
Composer 2.5 leads Qwen3.6-27B on 2 of the 2 benchmarks they both report (SWE-Bench Multilingual, Terminal-Bench 2.0). Qwen3.6-27B shipped 26 days before Composer 2.5, so benchmark comparisons should account for the intervening progress.
Qwen3.6-27B is open weight, while Composer 2.5 is closed.
On SWE-Bench Multilingual, Composer 2.5 leads at 79.8% vs Qwen3.6-27B at 71.3%. On Terminal-Bench 2.0, Composer 2.5 leads at 69.3% vs Qwen3.6-27B at 59.3%.