wehub-resource-sync
116 lines
2.3 KiB
TOML
116 lines
2.3 KiB
TOML
name = "GPT-5.6 Sol"
|
|
description = "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows"
|
|
family = "gpt-sol"
|
|
release_date = "2026-07-09"
|
|
last_updated = "2026-07-09"
|
|
attachment = true
|
|
reasoning = true
|
|
temperature = false
|
|
tool_call = true
|
|
structured_output = true
|
|
knowledge = "2026-02-16"
|
|
open_weights = false
|
|
|
|
[limit]
|
|
context = 1_050_000
|
|
input = 922_000
|
|
output = 128_000
|
|
|
|
[modalities]
|
|
input = ["text", "image", "pdf"]
|
|
output = ["text"]
|
|
|
|
[[benchmarks]]
|
|
name = "SWE-Bench Pro"
|
|
score = 64.6
|
|
metric = "resolve rate"
|
|
source = "https://openai.com/index/gpt-5-6/"
|
|
date = "2026-07-09"
|
|
|
|
[[benchmarks]]
|
|
name = "Terminal-Bench"
|
|
score = 88.8
|
|
metric = "success rate"
|
|
version = "2.1"
|
|
source = "https://openai.com/index/gpt-5-6/"
|
|
date = "2026-07-09"
|
|
|
|
[[benchmarks]]
|
|
name = "DeepSWE"
|
|
score = 72.7
|
|
metric = "resolve rate"
|
|
version = "1.1"
|
|
source = "https://openai.com/index/gpt-5-6/"
|
|
date = "2026-07-09"
|
|
|
|
[[benchmarks]]
|
|
name = "GPQA Diamond"
|
|
score = 94.6
|
|
metric = "accuracy"
|
|
source = "https://openai.com/index/gpt-5-6/"
|
|
date = "2026-07-09"
|
|
|
|
[[benchmarks]]
|
|
name = "FrontierMath"
|
|
score = 89
|
|
metric = "accuracy"
|
|
dataset = "Tier 1-3"
|
|
version = "v2"
|
|
source = "https://openai.com/index/gpt-5-6/"
|
|
date = "2026-07-09"
|
|
|
|
[[benchmarks]]
|
|
name = "BrowseComp"
|
|
score = 90.4
|
|
metric = "accuracy"
|
|
source = "https://openai.com/index/gpt-5-6/"
|
|
date = "2026-07-09"
|
|
|
|
[[benchmarks]]
|
|
name = "OSWorld"
|
|
score = 62.6
|
|
metric = "success rate"
|
|
version = "2.0"
|
|
source = "https://openai.com/index/gpt-5-6/"
|
|
date = "2026-07-09"
|
|
|
|
[[benchmarks]]
|
|
name = "MMMU Pro"
|
|
score = 83
|
|
metric = "accuracy"
|
|
variant = "no tools"
|
|
source = "https://openai.com/index/gpt-5-6/"
|
|
date = "2026-07-09"
|
|
|
|
[[benchmarks]]
|
|
name = "Agents' Last Exam"
|
|
score = 52.7
|
|
source = "https://openai.com/index/gpt-5-6/"
|
|
date = "2026-07-09"
|
|
|
|
[[benchmarks]]
|
|
name = "Toolathlon"
|
|
score = 58
|
|
metric = "success rate"
|
|
source = "https://openai.com/index/gpt-5-6/"
|
|
date = "2026-07-09"
|
|
|
|
[[benchmarks]]
|
|
name = "Artificial Analysis Intelligence Index"
|
|
score = 58.9
|
|
metric = "index score"
|
|
variant = "max"
|
|
version = "4.1"
|
|
source = "https://artificialanalysis.ai/articles/gpt-5-6-has-landed"
|
|
date = "2026-07-09"
|
|
|
|
[[benchmarks]]
|
|
name = "Artificial Analysis Coding Agent Index"
|
|
score = 80
|
|
metric = "index score"
|
|
harness = "Codex"
|
|
variant = "max"
|
|
version = "1.1"
|
|
source = "https://artificialanalysis.ai/articles/gpt-5-6-has-landed"
|
|
date = "2026-07-09"
|