chore: import upstream snapshot with attribution
This commit is contained in:
wehub-resource-sync
@@ -0,0 +1,20 @@
|
||||
name = "Gemini 2.0 Flash-Lite"
|
||||
description = "Low-latency Gemini model for high-volume multimodal and agent workloads"
|
||||
family = "gemini-flash-lite"
|
||||
release_date = "2024-12-11"
|
||||
last_updated = "2024-12-11"
|
||||
attachment = true
|
||||
reasoning = false
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
knowledge = "2024-06"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 8_192
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "audio", "video", "pdf"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,20 @@
|
||||
name = "Gemini 2.0 Flash"
|
||||
description = "Earlier Gemini Flash workhorse for responsive multimodal apps and tool use"
|
||||
family = "gemini-flash"
|
||||
release_date = "2024-12-11"
|
||||
last_updated = "2024-12-11"
|
||||
attachment = true
|
||||
reasoning = false
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
knowledge = "2024-06"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 8_192
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "audio", "video", "pdf"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,19 @@
|
||||
name = "Nano Banana"
|
||||
description = "Nano Banana image model for fast generation, edits, and character-consistent assets"
|
||||
family = "gemini-flash"
|
||||
release_date = "2025-08-26"
|
||||
last_updated = "2025-08-26"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = false
|
||||
knowledge = "2024-06"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 32_768
|
||||
output = 32_768
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image"]
|
||||
output = ["text", "image"]
|
||||
@@ -0,0 +1,41 @@
|
||||
name = "Gemini 2.5 Flash-Lite"
|
||||
description = "Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents"
|
||||
family = "gemini-flash-lite"
|
||||
release_date = "2025-06-17"
|
||||
last_updated = "2025-06-17"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 65_536
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "audio", "video", "pdf"]
|
||||
output = ["text"]
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Artificial Analysis Coding Index"
|
||||
score = 9.5
|
||||
metric = "index"
|
||||
source = "https://openrouter.ai/google/gemini-2.5-flash-lite/benchmarks"
|
||||
date = "2026-03-11"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SciCode"
|
||||
score = 19.3
|
||||
metric = "percent correct"
|
||||
source = "https://openrouter.ai/google/gemini-2.5-flash-lite/benchmarks"
|
||||
date = "2026-03-11"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Terminal-Bench Hard"
|
||||
score = 4.5
|
||||
metric = "success rate"
|
||||
source = "https://openrouter.ai/google/gemini-2.5-flash-lite/benchmarks"
|
||||
date = "2026-03-11"
|
||||
@@ -0,0 +1,19 @@
|
||||
name = "Gemini 2.5 Flash TTS"
|
||||
description = "Speech generation model for controllable voice, narration, and audio delivery"
|
||||
family = "gemini-flash"
|
||||
release_date = "2025-09-30"
|
||||
last_updated = "2025-12-10"
|
||||
attachment = false
|
||||
reasoning = false
|
||||
temperature = true
|
||||
tool_call = false
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 32_768
|
||||
output = 16_384
|
||||
|
||||
[modalities]
|
||||
input = ["text"]
|
||||
output = ["audio"]
|
||||
@@ -0,0 +1,48 @@
|
||||
name = "Gemini 2.5 Flash"
|
||||
description = "Fast Gemini workhorse for multimodal apps where latency and price matter"
|
||||
family = "gemini-flash"
|
||||
release_date = "2025-06-17"
|
||||
last_updated = "2025-06-17"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 65_536
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "audio", "video", "pdf"]
|
||||
output = ["text"]
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Aider Polyglot"
|
||||
score = 55.1
|
||||
metric = "percent correct"
|
||||
source = "https://aider.chat/docs/leaderboards/"
|
||||
date = "2025-05-25"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Artificial Analysis Coding Index"
|
||||
score = 22.2
|
||||
metric = "index"
|
||||
source = "https://openrouter.ai/google/gemini-2.5-flash/benchmarks"
|
||||
date = "2026-06-02"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SciCode"
|
||||
score = 39.4
|
||||
metric = "percent correct"
|
||||
source = "https://openrouter.ai/google/gemini-2.5-flash/benchmarks"
|
||||
date = "2026-06-02"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Terminal-Bench Hard"
|
||||
score = 13.6
|
||||
metric = "success rate"
|
||||
source = "https://openrouter.ai/google/gemini-2.5-flash/benchmarks"
|
||||
date = "2026-06-02"
|
||||
@@ -0,0 +1,19 @@
|
||||
name = "Gemini 2.5 Pro TTS"
|
||||
description = "Speech generation model for controllable voice, narration, and audio delivery"
|
||||
family = "gemini-pro"
|
||||
release_date = "2025-09-30"
|
||||
last_updated = "2025-12-10"
|
||||
attachment = false
|
||||
reasoning = false
|
||||
temperature = false
|
||||
tool_call = false
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 32_768
|
||||
output = 16_384
|
||||
|
||||
[modalities]
|
||||
input = ["text"]
|
||||
output = ["audio"]
|
||||
@@ -0,0 +1,48 @@
|
||||
name = "Gemini 2.5 Pro"
|
||||
description = "Google's proven reasoning model for coding, math, and multimodal analysis"
|
||||
family = "gemini-pro"
|
||||
release_date = "2025-06-17"
|
||||
last_updated = "2025-06-17"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 65_536
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "audio", "video", "pdf"]
|
||||
output = ["text"]
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Aider Polyglot"
|
||||
score = 83.1
|
||||
metric = "percent correct"
|
||||
source = "https://aider.chat/docs/leaderboards/"
|
||||
date = "2025-06-06"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Artificial Analysis Coding Index"
|
||||
score = 32
|
||||
metric = "index"
|
||||
source = "https://openrouter.ai/google/gemini-2.5-pro/benchmarks"
|
||||
date = "2026-06-02"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SciCode"
|
||||
score = 42.8
|
||||
metric = "percent correct"
|
||||
source = "https://openrouter.ai/google/gemini-2.5-pro/benchmarks"
|
||||
date = "2026-06-02"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Terminal-Bench Hard"
|
||||
score = 26.5
|
||||
metric = "success rate"
|
||||
source = "https://openrouter.ai/google/gemini-2.5-pro/benchmarks"
|
||||
date = "2026-06-02"
|
||||
@@ -0,0 +1,48 @@
|
||||
name = "Gemini 3 Flash Preview"
|
||||
description = "New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs"
|
||||
family = "gemini-flash"
|
||||
release_date = "2025-12-17"
|
||||
last_updated = "2025-12-17"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 65_536
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "video", "audio", "pdf"]
|
||||
output = ["text"]
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Bench Pro"
|
||||
score = 34.63
|
||||
metric = "resolve rate"
|
||||
dataset = "public"
|
||||
source = "https://labs.scale.com/leaderboard/swe_bench_pro_public"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Atlas Codebase QnA"
|
||||
score = 8.2
|
||||
metric = "score"
|
||||
harness = "Mini-SWE-Agent"
|
||||
source = "https://labs.scale.com/leaderboard/sweatlas-qna"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Atlas Refactoring"
|
||||
score = 10
|
||||
metric = "score"
|
||||
harness = "Mini-SWE-Agent"
|
||||
source = "https://labs.scale.com/leaderboard/sweatlas-refactoring"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Atlas Test Writing"
|
||||
score = 30.3
|
||||
metric = "score"
|
||||
harness = "Mini-SWE-Agent"
|
||||
source = "https://labs.scale.com/leaderboard/sweatlas-tw"
|
||||
@@ -0,0 +1,19 @@
|
||||
name = "Nano Banana Pro"
|
||||
description = "Nano Banana Pro for higher-fidelity image generation and design-heavy edits"
|
||||
family = "gemini-pro"
|
||||
release_date = "2025-11-20"
|
||||
last_updated = "2025-11-20"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = false
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 65_536
|
||||
output = 32_768
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image"]
|
||||
output = ["text", "image"]
|
||||
@@ -0,0 +1,19 @@
|
||||
name = "Nano Banana Pro"
|
||||
description = "Nano Banana Pro for higher-fidelity image generation and design-heavy edits"
|
||||
family = "gemini-pro"
|
||||
release_date = "2026-05-28"
|
||||
last_updated = "2026-05-28"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = false
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 65_536
|
||||
output = 32_768
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image"]
|
||||
output = ["text", "image"]
|
||||
@@ -0,0 +1,27 @@
|
||||
name = "Gemini 3 Pro Preview"
|
||||
description = "Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts"
|
||||
family = "gemini-pro"
|
||||
release_date = "2025-11-18"
|
||||
last_updated = "2025-11-18"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 65_536
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "video", "audio", "pdf"]
|
||||
output = ["text"]
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Bench Pro"
|
||||
score = 43.3
|
||||
metric = "resolve rate"
|
||||
dataset = "public"
|
||||
source = "https://labs.scale.com/leaderboard/swe_bench_pro_public"
|
||||
@@ -0,0 +1,19 @@
|
||||
name = "Nano Banana 2"
|
||||
description = "Image model for prompt-driven generation, editing, and visual design workflows"
|
||||
family = "gemini-flash"
|
||||
release_date = "2026-02-26"
|
||||
last_updated = "2026-02-26"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = false
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 65_536
|
||||
output = 65_536
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "pdf"]
|
||||
output = ["text", "image"]
|
||||
@@ -0,0 +1,19 @@
|
||||
name = "Nano Banana 2"
|
||||
description = "Image model for prompt-driven generation, editing, and visual design workflows"
|
||||
family = "gemini-flash"
|
||||
release_date = "2026-05-28"
|
||||
last_updated = "2026-05-28"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = false
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 131_072
|
||||
output = 32_768
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "video", "pdf"]
|
||||
output = ["text", "image"]
|
||||
@@ -0,0 +1,20 @@
|
||||
name = "Gemini 3.1 Flash Lite Preview"
|
||||
description = "Low-latency Gemini model for high-volume multimodal and agent workloads"
|
||||
family = "gemini-flash-lite"
|
||||
release_date = "2026-03-03"
|
||||
last_updated = "2026-03-03"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 65_536
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "video", "audio", "pdf"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,20 @@
|
||||
name = "Gemini 3.1 Flash Lite"
|
||||
description = "Low-latency Gemini model for high-volume multimodal and agent workloads"
|
||||
family = "gemini-flash-lite"
|
||||
release_date = "2026-05-07"
|
||||
last_updated = "2026-05-07"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 65_536
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "video", "audio", "pdf"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,20 @@
|
||||
name = "Gemini 3.1 Pro Preview Custom Tools"
|
||||
description = "Advanced Gemini model for complex reasoning, coding, and multimodal analysis"
|
||||
family = "gemini-pro"
|
||||
release_date = "2026-02-19"
|
||||
last_updated = "2026-02-19"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 65_536
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "video", "audio", "pdf"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,157 @@
|
||||
name = "Gemini 3.1 Pro Preview"
|
||||
description = "Reasoning-first Gemini preview for agentic coding and complex problem solving"
|
||||
family = "gemini-pro"
|
||||
release_date = "2026-02-19"
|
||||
last_updated = "2026-02-19"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 65_536
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "video", "audio", "pdf"]
|
||||
output = ["text"]
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Bench Pro"
|
||||
score = 54.2
|
||||
metric = "resolve rate"
|
||||
source = "https://www.anthropic.com/news/claude-opus-4-8"
|
||||
date = "2026-05-28"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Terminal-Bench"
|
||||
score = 70.3
|
||||
metric = "success rate"
|
||||
harness = "Terminus-2"
|
||||
version = "2.1"
|
||||
source = "https://www.anthropic.com/news/claude-opus-4-8"
|
||||
date = "2026-05-28"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Bench Pro"
|
||||
score = 46.1
|
||||
metric = "resolve rate"
|
||||
dataset = "public"
|
||||
source = "https://labs.scale.com/leaderboard/swe_bench_pro_public"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Atlas Codebase QnA"
|
||||
score = 13.5
|
||||
metric = "score"
|
||||
harness = "Mini-SWE-Agent"
|
||||
source = "https://labs.scale.com/leaderboard/sweatlas-qna"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Atlas Refactoring"
|
||||
score = 33.81
|
||||
metric = "score"
|
||||
harness = "Gemini CLI"
|
||||
source = "https://labs.scale.com/leaderboard/sweatlas-refactoring"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Atlas Test Writing"
|
||||
score = 29.84
|
||||
metric = "score"
|
||||
harness = "Mini-SWE-Agent"
|
||||
source = "https://labs.scale.com/leaderboard/sweatlas-tw"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Artificial Analysis Coding Agent Index"
|
||||
score = 43
|
||||
metric = "average pass@1"
|
||||
harness = "Gemini CLI"
|
||||
variant = "high"
|
||||
source = "https://artificialanalysis.ai/agents/coding-agents"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Atlas Codebase QnA"
|
||||
score = 45.6
|
||||
metric = "pass@1"
|
||||
harness = "Gemini CLI"
|
||||
variant = "high"
|
||||
source = "https://artificialanalysis.ai/agents/coding-agents"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Bench Pro"
|
||||
score = 15.1
|
||||
metric = "pass@1"
|
||||
harness = "Gemini CLI"
|
||||
variant = "high"
|
||||
dataset = "hard-aa"
|
||||
source = "https://artificialanalysis.ai/agents/coding-agents"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Terminal-Bench"
|
||||
score = 68.3
|
||||
metric = "pass@1"
|
||||
harness = "Gemini CLI"
|
||||
variant = "high"
|
||||
version = "2.1"
|
||||
source = "https://artificialanalysis.ai/agents/coding-agents"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "GPQA Diamond"
|
||||
score = 94.3
|
||||
metric = "accuracy"
|
||||
source = "https://openai.com/index/introducing-gpt-5-5/"
|
||||
date = "2026-04-23"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Humanity's Last Exam"
|
||||
score = 44.4
|
||||
metric = "accuracy"
|
||||
dataset = "full set, text + MM"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "ARC-AGI-2"
|
||||
score = 77.1
|
||||
metric = "accuracy"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "MMMU Pro"
|
||||
score = 80.5
|
||||
metric = "accuracy"
|
||||
variant = "no tools"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "MCP Atlas"
|
||||
score = 78.2
|
||||
metric = "success rate"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "OSWorld-Verified"
|
||||
score = 76.2
|
||||
metric = "success rate"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "CharXiv Reasoning"
|
||||
score = 83.3
|
||||
metric = "accuracy"
|
||||
variant = "no tools"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "GDPval-AA"
|
||||
score = 1314
|
||||
metric = "Elo"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
@@ -0,0 +1,97 @@
|
||||
name = "Gemini 3.5 Flash"
|
||||
description = "Fast Gemini model balancing multimodal reasoning, tool use, and cost"
|
||||
family = "gemini-flash"
|
||||
release_date = "2026-05-19"
|
||||
last_updated = "2026-05-19"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 65_536
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "video", "audio", "pdf"]
|
||||
output = ["text"]
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Terminal-Bench"
|
||||
score = 76.2
|
||||
metric = "success rate"
|
||||
harness = "Terminus-2"
|
||||
version = "2.1"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "SWE-Bench Pro"
|
||||
score = 55.1
|
||||
metric = "resolve rate"
|
||||
variant = "single attempt"
|
||||
dataset = "public"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "MCP Atlas"
|
||||
score = 83.6
|
||||
metric = "success rate"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Toolathlon"
|
||||
score = 56.5
|
||||
metric = "success rate"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "OSWorld-Verified"
|
||||
score = 78.4
|
||||
metric = "success rate"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "MMMU Pro"
|
||||
score = 83.6
|
||||
metric = "accuracy"
|
||||
variant = "no tools"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "CharXiv Reasoning"
|
||||
score = 84.2
|
||||
metric = "accuracy"
|
||||
variant = "no tools"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "Humanity's Last Exam"
|
||||
score = 40.2
|
||||
metric = "accuracy"
|
||||
dataset = "full set, text + MM"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "ARC-AGI-2"
|
||||
score = 72.1
|
||||
metric = "accuracy"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
|
||||
[[benchmarks]]
|
||||
name = "GDPval-AA"
|
||||
score = 1656
|
||||
metric = "Elo"
|
||||
source = "https://deepmind.google/models/gemini/flash/"
|
||||
date = "2026-05-19"
|
||||
@@ -0,0 +1,19 @@
|
||||
name = "Gemini Embedding 001"
|
||||
description = "Embedding model for semantic search, retrieval, clustering, and ranking pipelines"
|
||||
family = "gemini"
|
||||
release_date = "2025-05-20"
|
||||
last_updated = "2025-05-20"
|
||||
attachment = false
|
||||
reasoning = false
|
||||
temperature = false
|
||||
tool_call = false
|
||||
knowledge = "2025-05"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 2_048
|
||||
output = 1
|
||||
|
||||
[modalities]
|
||||
input = ["text"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,20 @@
|
||||
name = "Gemini Flash Latest"
|
||||
description = "Fast Gemini model balancing multimodal reasoning, tool use, and cost"
|
||||
family = "gemini-flash"
|
||||
release_date = "2025-09-25"
|
||||
last_updated = "2025-09-25"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 65_536
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "audio", "video", "pdf"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,20 @@
|
||||
name = "Gemini Flash-Lite Latest"
|
||||
description = "Low-latency Gemini model for high-volume multimodal and agent workloads"
|
||||
family = "gemini-flash-lite"
|
||||
release_date = "2025-09-25"
|
||||
last_updated = "2025-09-25"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
knowledge = "2025-01"
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 65_536
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "audio", "video", "pdf"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,24 @@
|
||||
name = "Gemini Omni Flash Preview"
|
||||
description = "Video generation and editing model for fast, conversational text- and image-to-video workflows"
|
||||
family = "gemini"
|
||||
release_date = "2026-06-30"
|
||||
last_updated = "2026-06-30"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
tool_call = false
|
||||
open_weights = false
|
||||
|
||||
[limit]
|
||||
context = 1_048_576
|
||||
output = 57_920
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "video"]
|
||||
output = ["video"]
|
||||
|
||||
[[benchmarks]]
|
||||
name = "LMArena Text-to-Video Arena"
|
||||
score = 1527
|
||||
metric = "Elo"
|
||||
source = "https://venturebeat.com/technology/googles-gemini-omni-flash-hits-the-api-turning-enterprise-video-production-into-a-conversation"
|
||||
date = "2026-06-30"
|
||||
@@ -0,0 +1,23 @@
|
||||
name = "Gemma 4 26B A4B IT"
|
||||
description = "Open Gemma instruction model for efficient chat and self-hosted deployments"
|
||||
family = "gemma"
|
||||
release_date = "2026-04-02"
|
||||
last_updated = "2026-04-02"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
open_weights = true
|
||||
|
||||
[limit]
|
||||
context = 262_144
|
||||
output = 32_768
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image"]
|
||||
output = ["text"]
|
||||
|
||||
[[weights]]
|
||||
label = "Hugging Face"
|
||||
url = "https://huggingface.co/google/gemma-4-26B-A4B-it"
|
||||
@@ -0,0 +1,23 @@
|
||||
name = "Gemma 4 31B IT"
|
||||
description = "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning"
|
||||
family = "gemma"
|
||||
release_date = "2026-04-02"
|
||||
last_updated = "2026-04-02"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
open_weights = true
|
||||
|
||||
[limit]
|
||||
context = 262_144
|
||||
output = 32_768
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image"]
|
||||
output = ["text"]
|
||||
|
||||
[[weights]]
|
||||
label = "Hugging Face"
|
||||
url = "https://huggingface.co/google/gemma-4-31B-it"
|
||||
@@ -0,0 +1,23 @@
|
||||
name = "Gemma 4 E2B IT"
|
||||
description = "Open Gemma instruction model for efficient chat and self-hosted deployments"
|
||||
family = "gemma"
|
||||
release_date = "2026-04-02"
|
||||
last_updated = "2026-04-02"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
open_weights = true
|
||||
|
||||
[limit]
|
||||
context = 131_072
|
||||
output = 8_192
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "audio"]
|
||||
output = ["text"]
|
||||
|
||||
[[weights]]
|
||||
label = "Hugging Face"
|
||||
url = "https://huggingface.co/google/gemma-4-E2B-it"
|
||||
@@ -0,0 +1,23 @@
|
||||
name = "Gemma 4 E4B IT"
|
||||
description = "Open Gemma instruction model for efficient chat and self-hosted deployments"
|
||||
family = "gemma"
|
||||
release_date = "2026-04-02"
|
||||
last_updated = "2026-04-02"
|
||||
attachment = true
|
||||
reasoning = true
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = true
|
||||
open_weights = true
|
||||
|
||||
[limit]
|
||||
context = 131_072
|
||||
output = 8_192
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image", "audio"]
|
||||
output = ["text"]
|
||||
|
||||
[[weights]]
|
||||
label = "Hugging Face"
|
||||
url = "https://huggingface.co/google/gemma-4-E4B-it"
|
||||
Reference in New Issue
Block a user