GPT-5.4 minivsQwen3-Coder-Next
GPT-5.4 mini | Qwen3-Coder-Next | |
|---|---|---|
| Specifications | ||
Parameters | — | 80B |
Context window | 400k | 256k |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given 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. | 32% | — |
Agentic coding SWE-Bench ProCan 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. | — | 44.3% |
Coding SWE-Bench VerifiedReal 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. | — | 70.6% |
Multilingual coding SWE-Bench MultilingualLike SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 62.8% |
Supabase coding Supabase Evals · with skillsSupabase's own open benchmark: a coding agent is dropped into a real Supabase project and asked to do real work — set up a schema, fix a broken security policy, debug an Edge Function — and every run is checked against a live Supabase stack. This is the headline number, where the agent has Supabase's own skills loaded, as most people building on Supabase would. The score is the share of scenarios it got right. Higher is better. | 78.9% | — |
Supabase coding Supabase Evals · no skillsThe same Supabase scenarios, but with none of Supabase's skills loaded — so it measures what the model already knows about building on Supabase, rather than how well it follows Supabase's supplied instructions. Higher is better. | 73.7% | — |
Agentic terminal coding Terminal-Bench 2.0Can 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. | — | 36.2% |
Browser agent BU BenchCan the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | 36% | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | 1398 | — |
| Overview | ||
| Company | OpenAI | Qwen |
| Release date | Mar 17 2026 | Feb 3 2026 |
| Access | Proprietary | Open Weight |
Which is better: GPT-5.4 mini or Qwen3-Coder-Next?
GPT-5.4 mini and Qwen3-Coder-Next don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen3-Coder-Next shipped 42 days before GPT-5.4 mini, so benchmark comparisons should account for the intervening progress.
Context windows are 400k (GPT-5.4 mini) vs 256k (Qwen3-Coder-Next). GPT-5.4 mini is proprietary, while Qwen3-Coder-Next is open weight.
Direct benchmark comparisons are unavailable — GPT-5.4 mini and Qwen3-Coder-Next don't publish scores on any of the same benchmarks.
Frequently asked questions
GPT-5.4 mini was released by OpenAI on Mar 17 2026.
Qwen3-Coder-Next was released by Qwen on Feb 3 2026.
GPT-5.4 mini has a 400k context window; Qwen3-Coder-Next has 256k.
GPT-5.4 mini is a proprietary model released by OpenAI. Qwen3-Coder-Next is an open weight model released by Qwen.