Atria Dawn Preview

Atria Dawn Preview is a reasoning model from Shanghai Artificial Intelligence Laboratory in the Atria Dawn family. 10 benchmarks count toward its score, in 2 categories.

partialShows if the model has enough results for an index.
IndexOverall score out of 100.Unranked
CoverageShare of the index weight with results.40%
SpeedOutput tokens per second.
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.256K
EloLMArena rating and rank.N/A

The index is a score out of 100. The ± range shows how much it can change.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
69.0
CodingCode writing and repair.
61.6
ReasoningLogic problems and puzzles.
N/A
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
N/A
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
N/A
MathMath problems.
N/A

Results

10 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
DeepSearchQAAgentic96.0%74.4Meta AI
BrowseCompAgentic92.5%77.4OpenAI
CyberGymAgentic86.5%75.3Zhun Wang et al.
MLE-Bench LiteAgentic86.2%MiniMax
WideResearchAgentic81.9%67.9Qwen
Terminal-Bench 2.1 (provider run)Agentic78.3%70.3DeepSeek-AI
Terminal-Bench 2.1 (provider run)Agentic78.3%70.3DeepSeek-AI
Berkeley Function Calling Leaderboard v4Agentic77.0%62.1Arcee AI
SWE-bench ProCoding59.6%61.6Xiang Deng et al.
AutomationBenchAgentic53.8%95.0Moonshot AI
JobBenchAgentic50.3%68.7Yuetai Li et al.
τ³-Bench Tool-Agent-User EvaluationAgentic41.2%30.2Sierra Research

10 benchmarks count, from 11 of 12 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authors