GPT-5.3-Codex-Spark vs Qwen3.5 397B

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

GPT-5.3-Codex-Spark is clearly ahead on the aggregate, 87 to 62. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.3-Codex-Spark's sharpest advantage is in coding, where it averages 82.3 against 40.7. The single biggest benchmark swing on the page is SWE-bench Pro, 85 to 42.

GPT-5.3-Codex-Spark is also the more expensive model on tokens at $2.00 input / $8.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen3.5 397B. That is roughly Infinityx on output cost alone. GPT-5.3-Codex-Spark is the reasoning model in the pair, while Qwen3.5 397B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GPT-5.3-Codex-Spark gives you the larger context window at 256K, compared with 128K for Qwen3.5 397B.

Quick Verdict

Pick GPT-5.3-Codex-Spark if you want the stronger benchmark profile. Qwen3.5 397B only becomes the better choice if you want the cheaper token bill or you would rather avoid the extra latency and token burn of a reasoning model.

Agentic

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

85.6

Qwen3.5 397B

56.9

90
Terminal-Bench 2.0
58
82
BrowseComp
62
83
OSWorld-Verified
52

Coding

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

82.3

Qwen3.5 397B

40.7

91
HumanEval
75
80
SWE-bench Verified
42
80
LiveCodeBench
39
85
SWE-bench Pro
42

Multimodal & Grounded

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

88.3

Qwen3.5 397B

61.4

86
MMMU-Pro
56
91
OfficeQA Pro
68

Reasoning

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

92.7

Qwen3.5 397B

75.9

94
SimpleQA
80
92
MuSR
78
97
BBH
82
91
LongBench v2
72
92
MRCRv2
71

Knowledge

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

78.3

Qwen3.5 397B

59.3

97
MMLU
83
95
GPQA
82
93
SuperGPQA
80
91
OpenBookQA
78
88
MMLU-Pro
73
42
HLE
10
88
FrontierScience
71

Instruction Following

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

92

Qwen3.5 397B

82

92
IFEval
82

Multilingual

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

90.8

Qwen3.5 397B

78.8

94
MGSM
82
89
MMLU-ProX
77

Mathematics

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

96.7

Qwen3.5 397B

81.6

98
AIME 2023
83
98
AIME 2024
85
97
AIME 2025
84
94
HMMT Feb 2023
79
96
HMMT Feb 2024
81
95
HMMT Feb 2025
80
95
BRUMO 2025
82
98
MATH-500
81

Frequently Asked Questions

Which is better, GPT-5.3-Codex-Spark or Qwen3.5 397B?

GPT-5.3-Codex-Spark is ahead overall, 87 to 62. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 85 and 42.

Which is better for knowledge tasks, GPT-5.3-Codex-Spark or Qwen3.5 397B?

GPT-5.3-Codex-Spark has the edge for knowledge tasks in this comparison, averaging 78.3 versus 59.3. Inside this category, HLE is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-5.3-Codex-Spark or Qwen3.5 397B?

GPT-5.3-Codex-Spark has the edge for coding in this comparison, averaging 82.3 versus 40.7. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, GPT-5.3-Codex-Spark or Qwen3.5 397B?

GPT-5.3-Codex-Spark has the edge for math in this comparison, averaging 96.7 versus 81.6. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GPT-5.3-Codex-Spark or Qwen3.5 397B?

GPT-5.3-Codex-Spark has the edge for reasoning in this comparison, averaging 92.7 versus 75.9. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-5.3-Codex-Spark or Qwen3.5 397B?

GPT-5.3-Codex-Spark has the edge for agentic tasks in this comparison, averaging 85.6 versus 56.9. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, GPT-5.3-Codex-Spark or Qwen3.5 397B?

GPT-5.3-Codex-Spark has the edge for multimodal and grounded tasks in this comparison, averaging 88.3 versus 61.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, GPT-5.3-Codex-Spark or Qwen3.5 397B?

GPT-5.3-Codex-Spark has the edge for instruction following in this comparison, averaging 92 versus 82. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, GPT-5.3-Codex-Spark or Qwen3.5 397B?

GPT-5.3-Codex-Spark has the edge for multilingual tasks in this comparison, averaging 90.8 versus 78.8. Inside this category, MGSM is the benchmark that creates the most daylight between them.

Last updated: March 12, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.