Compare AI models
| These models have no shared benchmark scores. | ||
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 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. | — | 79.8% |
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. | — | 81% |
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% |
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. | — | 69.3% |
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. | — | 1077 |
| Overview | ||
| Company | DeepSeek | SpaceXSI |
| Release date | Jan 20 2025 | May 18 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek Chat (R1-based)vsClaude Haiku 5.5Composer 2.5vsClaude Haiku 5.5DeepSeek Chat (R1-based)vsGPT-6.1 SolComposer 2.5vsGPT-6.1 SolDeepSeek Chat (R1-based)vsGemini 4 ArgonComposer 2.5vsGemini 4 ArgonDeepSeek Chat (R1-based)vsMuse Spark OpenComposer 2.5vsMuse Spark OpenDeepSeek Chat (R1-based)vsMistral Large 4Composer 2.5vsMistral Large 4DeepSeek Chat (R1-based)vsKimi K3.1 ProComposer 2.5vsKimi K3.1 ProFrequently asked questions
DeepSeek Chat (R1-based) and Composer 2.5 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek Chat (R1-based) shipped 483 days before Composer 2.5, so benchmark comparisons should account for the intervening progress.
DeepSeek Chat (R1-based) is open weight, while Composer 2.5 is closed.
Direct benchmark comparisons are unavailable — DeepSeek Chat (R1-based) and Composer 2.5 don't publish scores on any of the same benchmarks.