Compare · ModelsLive · 2 picked · head to head
GPT-5.3-Codex vs Qwen3.5 397B A17B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5.3-Codex wins on 12/12 benchmarks
GPT-5.3-Codex wins 12 of 12 shared benchmarks. Leads in speed · agentic.
Category leads
speed·GPT-5.3-Codexagentic·GPT-5.3-Codex
Hype vs Reality
Attention vs performance
GPT-5.3-Codex
#83 by perf·#9 by attention
Qwen3.5 397B A17B
#53 by perf·#1 by attention
Best value
Qwen3.5 397B A17B
4.1x better value than GPT-5.3-Codex
GPT-5.3-Codex
7.0 pts/$
$7.88/M
Qwen3.5 397B A17B
28.7 pts/$
$2.10/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
12 benchmarks · 2 models
GPT-5.3-CodexQwen3.5 397B A17B
Artificial Analysis · Agentic Index
GPT-5.3-Codex leads by +42.3
Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?"
GPT-5.3-Codex
62.2
Qwen3.5 397B A17B
19.9
Artificial Analysis · Coding Index
GPT-5.3-Codex leads by +4.9
Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads.
GPT-5.3-Codex
53.1
Qwen3.5 397B A17B
48.2
Artificial Analysis · CritPt
GPT-5.3-Codex leads by +16.0
GPT-5.3-Codex
16.9
Qwen3.5 397B A17B
0.9
Artificial Analysis · GPQA Diamond
GPT-5.3-Codex leads by +5.4
GPT-5.3-Codex
91.5
Qwen3.5 397B A17B
86.1
Artificial Analysis · Humanity's Last Exam
GPT-5.3-Codex leads by +22.7
GPT-5.3-Codex
42.5
Qwen3.5 397B A17B
19.8
Artificial Analysis · IFBench
GPT-5.3-Codex leads by +23.8
GPT-5.3-Codex
75.4
Qwen3.5 397B A17B
51.6
Artificial Analysis · Long Context Reasoning
GPT-5.3-Codex leads by +19.0
GPT-5.3-Codex
83.3
Qwen3.5 397B A17B
64.3
Artificial Analysis · MMMU Pro
GPT-5.3-Codex leads by +25.8
GPT-5.3-Codex
78.5
Qwen3.5 397B A17B
52.7
Artificial Analysis · Quality Index
GPT-5.3-Codex leads by +11.1
GPT-5.3-Codex
32.5
Qwen3.5 397B A17B
21.4
Artificial Analysis · tau2-Bench Telecom
GPT-5.3-Codex leads by +2.1
GPT-5.3-Codex
86.0
Qwen3.5 397B A17B
83.9
Artificial Analysis · Terminal-Bench Hard
GPT-5.3-Codex leads by +17.4
GPT-5.3-Codex
53.0
Qwen3.5 397B A17B
35.6
APEX-Agents
GPT-5.3-Codex leads by +6.8
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
GPT-5.3-Codex
31.7
Qwen3.5 397B A17B
24.9
Full benchmark table
| Benchmark | GPT-5.3-Codex | Qwen3.5 397B A17B |
|---|---|---|
Artificial Analysis · Agentic Index Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?" | 62.2 | 19.9 |
Artificial Analysis · Coding Index Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads. | 53.1 | 48.2 |
Artificial Analysis · CritPt | 16.9 | 0.9 |
Artificial Analysis · GPQA Diamond | 91.5 | 86.1 |
Artificial Analysis · Humanity's Last Exam | 42.5 | 19.8 |
Artificial Analysis · IFBench | 75.4 | 51.6 |
Artificial Analysis · Long Context Reasoning | 83.3 | 64.3 |
Artificial Analysis · MMMU Pro | 78.5 | 52.7 |
Artificial Analysis · Quality Index | 32.5 | 21.4 |
Artificial Analysis · tau2-Bench Telecom | 86.0 | 83.9 |
Artificial Analysis · Terminal-Bench Hard | 53.0 | 35.6 |
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 31.7 | 24.9 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $1.75 | $14.00 | 400K tokens (~200 books) | $48.13 | |
| $0.60 | $3.60 | 262K tokens (~131 books) | $13.50 |