GPT-5 Codex
Sep 2025
GPT-5 CodexCompare inon
Benchmarks of GPT-5 Codex20
BenchmarkByScoreRank
Overall1
Knowledge4
Science2
Coding1
Multimodal1
Documents1
Legacy · saturated or no longer reported10
No benchmark matches
Rankingat high effort?
Retired models are left out of the current rankings.
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperMuse Spark 1.3max+93%-42%$1.60Only auto tool_choice is supported+5BetterGPT-6 Lunamedium+20%-94%$0.017Function calling only with none · Chat Completions+3
OpenMiMo v2.6 Prothinking+86%-84%$0.13Pass back reasoning_content+3
CheaperGrok 4.7xhigh+87%-13%$3.74Reasoning cannot be disabled+4
CheaperQwen3.8 Max (0902)thinking+83%-13%$5.41ModelScoreCostPer taskWhat changes
Muse Spark 1.3max+93%-42%$1.60Only auto tool_choice is supported+5Grok 4.7xhigh+87%-13%$3.74Reasoning cannot be disabled+4MiMo v2.6 ProthinkingOpen+86%-84%$0.13Pass back reasoning_content+3Qwen3.8 Max (0902)thinking+83%-13%$5.41
DeepSeek V4.1 Flash 1017maxOpen+81%-85%$0.26Pass back reasoning_content · Chat Completions+4ModelScoreCostPer taskWhat changes
GPT-6 Lunamedium+20%-94%$0.017Function calling only with none · Chat Completions+3
Claude Haiku 5.5low+18%-94%$0.024Remove sampling parameters+5GPT-5.6 Lunahigh+29%-87%$0.044MiMo v2.6 FlashthinkingOpen+52%-95%$0.062Pass back reasoning_content+3GPT-6.1 Sollow+69%+16%$0.13Remove unsupported parameters+5ModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen+86%-84%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen+81%-85%$0.26Pass back reasoning_content · Chat Completions+4
GLM 5.3maxOpen+80%-37%$2.01No image input+4
Step 5 PreviewthinkingOpen+76%-59%$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen+75%+75%$2.00Sampling parameters are fixed+3ModelScoreCostPer taskWhat changes
GPT-6 Astrahigh×2—$1.73Monitoring can return HTTP 403+2GPT-6.1 Solhigh×2—$0.32Remove unsupported parameters+5GPT-6 Solhigh+70%—$0.37GPT-5.6 Solhigh+70%—$0.81GPT-5.5high+49%—$1.54Prompts with >272K input tokensGPT-5.6 Terrahigh+38%—$0.34Prompts with >272K input tokensGPT-6 Lunahigh+32%—$0.029Function calling only with none · Chat Completions+3GPT-5.3 Codexxhigh+31%—$1.75 / $14DeprecatedAll OpenAI models →History
4 versionsBenchmarks
all categoriesChat & Knowledge
GPQA Diamond83.7
Coding
Agents & Tool Use
τ²-bench · AA86.8
Writing & Language
Vision & Documents
FAQ
How much does GPT-5 Codex cost?›
$1.25 per 1M input tokens and $10 per 1M output tokens (cheapest host: Abacus).
Is GPT-5 Codex free to use?›
There is no free API; the cheapest paid price is $1.25 per 1M input tokens.
How can I use GPT-5 Codex?›
Through the OpenAI API.
What is the context window of GPT-5 Codex?›
400K tokens.
When was GPT-5 Codex released? Is there a newer version?›
Released 2025-09-23. It has been superseded by GPT-5.6 Sol.
Is GPT-5 Codex open source?›
No, GPT-5 Codex is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can GPT-5 Codex read images?›
It accepts text and images as input.
What is GPT-5 Codex?›
GPT-5 Codex is a closed language model from OpenAI, released Sep 2025.
What are the best alternatives to GPT-5 Codex?›
Muse Spark 1.3 (cheaper), GPT-6 Luna (better), MiMo v2.6 Pro (open weights).