Celeris-1

Celeris-1 is a non-reasoning model from Celeris. 12 benchmarks count toward its score, in 5 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.32.3 ±7.2
CoverageShare of the index weight with results.75%
SpeedOutput tokens per second.1492/s
Input / 1MUS dollars per 1M input tokens.$0.2
Output / 1MUS dollars per 1M output tokens.$0.7
ContextMaximum tokens in one request.128K
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.
36.6
CodingCode writing and repair.
26.0
ReasoningLogic problems and puzzles.
36.5
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
32.6
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
25.4
MathMath problems.
N/A

Results

12 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.
Grade School Math 8KMath93.7%DeepSeek-AI
Discrete Reasoning Over ParagraphsReasoning81.4%DeepSeek-AI
Instruction-Following EvalInstruction80.8%25.4Jeffrey Zhou et al.
Massive Multitask Language Understanding ProfessionalKnowledge75.9%40.1Yubo Wang et al.
Artificial Analysis GPQA DiamondKnowledge63.1%33.2Artificial Analysis
Artificial Analysis Long Context ReasoningReasoning38.0%34.6Artificial Analysis
Artificial Analysis SciCodeCoding21.6%22.9Artificial Analysis
Artificial Analysis Coding IndexCoding14.4%29.1Artificial Analysis
Artificial Analysis Omniscience AccuracyKnowledge11.0%27.5Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge6.8%31.9Artificial Analysis
Artificial Analysis Intelligence IndexKnowledge6.3%30.3Artificial Analysis
Artificial Analysis Agentic IndexAgentic0.7%37.7Artificial Analysis
GDPval-AA normalizedAgentic0.0%35.6Artificial Analysis
Critical Physics TasksReasoning0.0%38.4Artificial Analysis

12 benchmarks count, from 12 of 14 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

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeApodex 1.1 Mini59.1 · Free