llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1367 models808 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

Shanghai AI Laboratory model product

Atria Dawn

Atria Dawn is a preview-stage agentic model from Shanghai AI Laboratory with a 744B-parameter MoE architecture and a 256K-token context window.

Updated Oct 23, 2026. Default version: Atria Dawn Preview

LLMBoard Score83.3Atria Dawn Preview
Coverage0%11 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Similar models
  • About
  • FAQ

Atria Dawn Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

Atria Dawn Preview LLMBoard score breakdown

Atria Dawn Benchmark Results

Benchmark scores for Atria Dawn Preview.

12 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkBFCL-V4Score77.00%Rank01Participants22Percentile100.00%EvidenceCEvaluatedOct 12, 2026
BenchmarkBrowseCompScore92.50%Rank01Participants70Percentile100.00%EvidenceCEvaluatedOct 12, 2026
BenchmarkDeepSearchQAScore96.00%Rank01Participants13Percentile100.00%EvidenceCEvaluatedOct 12, 2026
BenchmarkMLE-Bench LiteScore86.20%Rank01Participants2Percentile100.00%EvidenceCEvaluatedOct 12, 2026
BenchmarkTau3 BankingScore41.20%Rank01Participants16Percentile100.00%EvidenceCEvaluatedOct 12, 2026
BenchmarkSkillsBenchScore66.40%Rank03Participants12Percentile81.82%EvidenceCEvaluatedOct 12, 2026
BenchmarkWideSearchScore81.90%Rank03Participants15Percentile85.71%EvidenceCEvaluatedOct 12, 2026
BenchmarkAutomationBenchScore53.80%Rank04Participants27Percentile88.46%EvidenceCEvaluatedOct 12, 2026
BenchmarkCyberGymScore86.50%Rank05Participants23Percentile81.82%EvidenceCEvaluatedOct 12, 2026
BenchmarkGDPval-AAScore1,583.00 pointsRank07Participants17Percentile62.50%EvidenceCEvaluatedOct 12, 2026
BenchmarkSWE-Bench ProScore59.60%Rank22Participants63Percentile66.13%EvidenceCEvaluatedOct 12, 2026
BenchmarkTerminal-Bench 2.1Score78.30%Rank25Participants48Percentile48.94%EvidenceCEvaluatedOct 12, 2026

Atria Dawn Arena Results

Preference and agent-evaluation results for the default version.

No Arena results

The default version does not have a matching Arena result yet.

Atria Dawn Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
0
No provider prices

The default version has no current input or output token prices.

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Atria Dawn Runtime Performance

Provider-specific output speed and catalog latency for Atria Dawn Preview. Runtime does not affect the capability score.

No runtime data

No provider-specific speed or latency record is linked to the default version yet.

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

Atria Dawn Specifications

Technical details for the model's default version.

Version
Atria Dawn Preview
Released
Sep 11, 2026
Knowledge cutoff
Unknown
Parameters
744B
Context window
N/A
Max output
N/A
Inputs
text
Outputs
text
Open weights
Yes
License
MIT

Atria Dawn Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionAtria Dawn PreviewReleasedSep 11, 2026LLMBoard83.28Parameters744BContextN/AMax outputN/AOpen weightsYesLicenseMIT

Models similar to Atria Dawn

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#17-0.07
DE

DeepSeek-V4.1

DeepSeek

83.21 LLMBoard

Details
#18-0.12
DE

DeepSeek-V4-Pro

DeepSeek

83.16 LLMBoard

Details
#15+0.18
ME

Muse Wonder Full

Meta

83.46 LLMBoard

Details
#19-0.21
AN

Claude Opus 4.8

Anthropic

83.07 LLMBoard

Details
#20-0.61
GO

Gemini 3.8 Flash

Google

82.67 LLMBoard

Details
#21-0.67
ME

Muse Spark 1.1

Meta

82.61 LLMBoard

Details

What is Atria Dawn?

Key information about Atria Dawn and its available data.

Atria Dawn is a text-only Instruct model from Shanghai AI Laboratory for research and engineering workflows involving environment understanding, tool use, and multi-step task completion. Its weights are available in BF16 and FP8 formats under the MIT license.

Data as of 2026-10-22.

FAQ

Common questions about Atria Dawn.

When was Atria Dawn released?

Atria Dawn's default version was released on Sep 11, 2026.

How much does Atria Dawn cost?

No official standard PAYG price is currently available for Atria Dawn.

Who created Atria Dawn?

Atria Dawn was created by Shanghai AI Laboratory.

What is the context window for Atria Dawn?

A context window is not available for the default version.

Is Atria Dawn open weight?

Yes. The default version is marked as open weight under MIT.

How many API providers offer Atria Dawn?

No provider offering is currently linked to the default version.

Browse runtime rankings