GPT-5.3 Codex
- Input
- $1.75/M tok
- Output
- $14/M tok
- Blended
- $4.813/M tok · 3:1
- Speed
- 102tok/s
- Context
- 400Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: GPT-5.3 Codex (xhigh). Price = AA median host price.
Rankings
Writing & chat
Verified#20 / 162rank by quality74.3±9.5quality / 1001/5 benchmarks measuredVision
Verified#20 / 98rank by quality73.3±8.2quality / 1001/6 benchmarks measuredHard reasoning
Verified#31 / 218rank by quality73.8±5.9quality / 1002/4 benchmarks measuredAgents
Verified#33 / 187rank by quality67.4±10.0quality / 1001/7 benchmarks measured
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Writing & chat
IFBenchVerified
#24 of 13975.4%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #23Gemma 4 31B75.6%
- #24GPT-5.3 Codex75.4%
- #25LFM2.5-24B-A2B74.7%
artificialanalysis.ai · 2026-09-24
LMArena Text, Non-English (Elo)Estimated
~#18 of 57 (estimated)~1452 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #17GPT-5.6 Terra1456
- ~#18GPT-5.3 CodexEstimated1452
- #18DeepSeek V4 Pro (0813)1448
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#18 of 57 (estimated)~1464 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #17GPT-5.6 Terra1466
- ~#18GPT-5.3 CodexEstimated1464
- #18DeepSeek V4 Pro (0813)1463
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#9 of 26 (estimated)~1963 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #8Grok 4.72007
- ~#9GPT-5.3 CodexEstimated1963
- #9Muse Spark 1.31906
No published score — estimated from related benchmarks
Vision
MMMU-ProVerified
#23 of 8778.5%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #22MiniMax-M378.6%
- #23GPT-5.3 Codex78.5%
- #24Qwen3.8 Flash-Next NVFP478.3%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~#5 of 12 (estimated)~82.9%
- #1Gemini 3.8 Flash86.2%
- #2Kimi K384.8%
- #4Qwen3.8-Omni-Flash83.5%
- ~#5GPT-5.3 CodexEstimated82.9%
- #5MiniMax-M3.1-Flash82.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~88.6%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #2Qwen3.8 27B91.1%
- ~#4GPT-5.3 CodexEstimated88.6%
- #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#19 of 48 (estimated)~19.3%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #18Grok 4.720.0%
- ~#19GPT-5.3 CodexEstimated19.3%
- #19MiMo-V2.6-Pro19.2%
No published score — estimated from related benchmarks
ChartographyEstimated
~#9 of 25 (estimated)~33.0%
- #1Claude Fable 5.273.4%
- #2GPT-6 Astra71.0%
- #8GPT-5.6 Terra34.0%
- ~#9GPT-5.3 CodexEstimated33.0%
- #9GPT-5.531.0%
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#22 of 19291.5%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #21GLM-5.391.7%
- #22GPT-5.3 Codex91.5%
- #22Qwen3.8 Flash-Next NVFP491.5%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#29 of 19842.5%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #28GPT-5.6 Terra42.9%
- #29GPT-5.3 Codex42.5%
- #30Qwen3.8 2.4T A95B42.4%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#2 of 34 (estimated)~99.1%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#33 of 103 (estimated)~38.6
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #32Muse Spark Open38.9
- ~#33GPT-5.3 CodexEstimated38.6
- #33GPT-5.538.4
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#25 of 11986.0%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #24GPT-5.6 Terra86.3%
- #25GPT-5.3 Codex86.0%
- #26GPT-5.4 mini83.3%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#9 of 15 (estimated)~75.0%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #8GPT-5.578.7%
- ~#9GPT-5.3 CodexEstimated75.0%
- #9Gemini 3.5 Flash-Lite74.0%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#14 of 22 (estimated)~79.8%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #13Nex-N2.5-Mini83.4%
- ~#14GPT-5.3 CodexEstimated79.8%
- #14Nemotron 3.5 Super VL78.0%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#20 of 92 (estimated)~1573 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #19GPT-6 Astra1574
- ~#20GPT-5.3 CodexEstimated1573
- #20Kimi K31533
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#29 of 85 (estimated)~45.2%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #28GPT-5.547.3%
- ~#29GPT-5.3 CodexEstimated45.2%
- #29K2 Horizon 375B A23B37.2%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#21 of 91 (estimated)~32.4%
- #1Muse Spark 1.350.5%
- #2GLM-5.350.3%
- #20K2 Horizon 375B A23B34.2%
- ~#21GPT-5.3 CodexEstimated32.4%
- #21K2 Horizon MoVA 36B A4B32.0%
No published score — estimated from related benchmarks