wehub-resource-sync
58 lines
1.2 KiB
TOML
58 lines
1.2 KiB
TOML
name = "MAI-Code-1-Flash"
|
|
description = "Microsoft coding model built for fast, efficient assistance in everyday developer workflows"
|
|
family = "mai"
|
|
release_date = "2026-06-02"
|
|
last_updated = "2026-06-08"
|
|
attachment = false
|
|
reasoning = true
|
|
temperature = true
|
|
tool_call = true
|
|
structured_output = true
|
|
knowledge = "2025-12"
|
|
open_weights = false
|
|
|
|
[limit]
|
|
context = 256_000
|
|
output = 128_000
|
|
|
|
[modalities]
|
|
input = ["text"]
|
|
output = ["text"]
|
|
|
|
[[links]]
|
|
label = "Model card"
|
|
url = "https://microsoft.ai/pdf/MAI-Code-1-Flash-Model-Card.PDF"
|
|
type = "model_card"
|
|
|
|
[[links]]
|
|
label = "Announcement"
|
|
url = "https://microsoft.ai/news/introducingmai-code-1-flash/"
|
|
type = "announcement"
|
|
|
|
[[benchmarks]]
|
|
name = "SWE-Bench Pro"
|
|
score = 51.2
|
|
metric = "resolve rate"
|
|
harness = "GitHub Copilot"
|
|
source = "https://microsoft.ai/news/introducingmai-code-1-flash/"
|
|
date = "2026-06-02"
|
|
|
|
[[benchmarks]]
|
|
name = "SWE-Bench Verified"
|
|
score = 71.6
|
|
metric = "resolved"
|
|
source = "https://llm-stats.com/benchmarks/swe-bench-verified"
|
|
|
|
[[benchmarks]]
|
|
name = "Terminal-Bench"
|
|
score = 54.8
|
|
metric = "success rate"
|
|
version = "2.0"
|
|
source = "https://llm-stats.com/benchmarks/terminal-bench-2"
|
|
|
|
[[benchmarks]]
|
|
name = "GPQA Diamond"
|
|
score = 84.6
|
|
metric = "accuracy"
|
|
source = "https://llm-stats.com/benchmarks/gpqa"
|