Compare · ModelsLive · 2 picked · head to head
GPT-5.1-Codex-Mini vs Qwen3 Next 80B A3B Thinking
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5.1-Codex-Mini wins on 7/8 benchmarks
GPT-5.1-Codex-Mini wins 7 of 8 shared benchmarks. Leads in coding · language · math.
Category leads
coding·GPT-5.1-Codex-Minireasoning·Qwen3 Next 80B A3B Thinkinglanguage·GPT-5.1-Codex-Minimath·GPT-5.1-Codex-Miniknowledge·GPT-5.1-Codex-Mini
Hype vs Reality
Attention vs performance
GPT-5.1-Codex-Mini
#39 by perf·no signal
Qwen3 Next 80B A3B Thinking
#32 by perf·no signal
Best value
Qwen3 Next 80B A3B Thinking
2.6x better value than GPT-5.1-Codex-Mini
GPT-5.1-Codex-Mini
53.7 pts/$
$1.13/M
Qwen3 Next 80B A3B Thinking
140.4 pts/$
$0.44/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
8 benchmarks · 2 models
GPT-5.1-Codex-MiniQwen3 Next 80B A3B Thinking
LiveBench · Agentic Coding
GPT-5.1-Codex-Mini leads by +31.7
GPT-5.1-Codex-Mini
40.0
Qwen3 Next 80B A3B Thinking
8.3
LiveBench · Coding
GPT-5.1-Codex-Mini leads by +9.3
GPT-5.1-Codex-Mini
69.9
Qwen3 Next 80B A3B Thinking
60.7
LiveBench · Data Analysis
Qwen3 Next 80B A3B Thinking leads by +3.9
GPT-5.1-Codex-Mini
49.7
Qwen3 Next 80B A3B Thinking
53.6
LiveBench · If
GPT-5.1-Codex-Mini leads by +17.5
GPT-5.1-Codex-Mini
59.0
Qwen3 Next 80B A3B Thinking
41.5
LiveBench · Language
GPT-5.1-Codex-Mini leads by +6.7
GPT-5.1-Codex-Mini
63.0
Qwen3 Next 80B A3B Thinking
56.3
LiveBench · Mathematics
GPT-5.1-Codex-Mini leads by +2.0
GPT-5.1-Codex-Mini
76.3
Qwen3 Next 80B A3B Thinking
74.3
LiveBench · Overall
GPT-5.1-Codex-Mini leads by +10.0
GPT-5.1-Codex-Mini
60.4
Qwen3 Next 80B A3B Thinking
50.4
LiveBench · Reasoning
GPT-5.1-Codex-Mini leads by +6.5
GPT-5.1-Codex-Mini
64.7
Qwen3 Next 80B A3B Thinking
58.2
Full benchmark table
| Benchmark | GPT-5.1-Codex-Mini | Qwen3 Next 80B A3B Thinking |
|---|---|---|
LiveBench · Agentic Coding | 40.0 | 8.3 |
LiveBench · Coding | 69.9 | 60.7 |
LiveBench · Data Analysis | 49.7 | 53.6 |
LiveBench · If | 59.0 | 41.5 |
LiveBench · Language | 63.0 | 56.3 |
LiveBench · Mathematics | 76.3 | 74.3 |
LiveBench · Overall | 60.4 | 50.4 |
LiveBench · Reasoning | 64.7 | 58.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| GPT-5.1-Codex-Mini | $0.25 | $2.00 | 400K tokens (~200 books) | $6.88 |
| Qwen3 Next 80B A3B Thinking | $0.10 | $0.78 | 131K tokens (~66 books) | $2.68 |
People also compared
Qwen3.5 397B A17B vs Qwen3 Next 80B A3B ThinkingQwen3.6 Plus vs Qwen3 Next 80B A3B ThinkingQwen3 30B A3B Thinking 2507 vs Qwen3 Next 80B A3B ThinkingMiniMax M2.7 vs Qwen3 Next 80B A3B ThinkingGemma 4 31B vs Qwen3 Next 80B A3B Thinkingo3 Pro vs Qwen3 Next 80B A3B Thinkingphi-3-mini 3.8B vs Qwen3 Next 80B A3B ThinkingQwen-14B vs Qwen3 Next 80B A3B Thinking