Translate
Independent model intelligence

Find the right AI model,
not just the loudest one.

Compare current model capability, context, modalities, public preference and API economics in one continuously refreshed decision surface.

LiveBench 2.0 LMArena models.dev OpenRouter AIHOT cross-check
Back to leaderboard
Independent · Active

Step 5 Preview

Multimodal model · launched 2026-09-16

MultimodalReasoningToolsStructuredOpen weights
AITopic score73.7#17 overall

StepFun flash model for efficient multimodal reasoning, coding, and tool use

Evidence coverage100%8 evaluations · 3 institutions
Context / maximum output1M / 1Mtokens
Cache / input / output$0.1 · $1 · $2.7USD per million tokens
Value / freshness73.6 / 88relative value · release freshness
Product profile

What this model supports

Inputtext, image
Outputtext
Knowledge cutoffNot disclosed
WeightsOpen weights
Capability profile

Strengths by domain

Coding85.62 public results
Research & reasoning83.81 public results
Professional work46.22 public results
Knowledge & instruction72.82 public results
Behind the score

Every result has a source

Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.

Coding2 results

LiveBench 2.0 · CodingLiveBench85.60 scoreReading 85.6

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0Open evidence
AIHOT · CodingAIHOT61.10 scoreReading 61.1

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Research & reasoning1 results

LiveBench 2.0 · ResearchLiveBench83.80 scoreReading 83.8

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0Open evidence

Professional work2 results

AIHOT · ProfessionalAIHOT61.40 scoreReading 61.4

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
LiveBench 2.0 · ProfessionalLiveBench46.15 scoreReading 46.2

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Professional = long-agentic, browser, data-analysis and design average.

Configuration: LiveBench 2.0Open evidence

Knowledge & instruction2 results

LiveBench 2.0 · KnowledgeLiveBench72.80 scoreReading 72.8

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Knowledge uses the published LiveBench research suite.

Configuration: LiveBench 2.0Open evidence
AIHOT · KnowledgeAIHOT61.50 scoreReading 61.5

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Human preference & indices4 results

Arena TextLMArena1,442.7 EloReading 74.1

Direct LMArena text leaderboard result.

Open evidence
LiveBenchLiveBench60.97 scoreReading 61.0

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0Open evidence
AIHOT aggregate leaderboardAIHOT60.70 scoreReading 60.7

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AA IndexArtificial Analysis64.00 indexReading 55.3

Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0Open evidence
Same builder

More from Independent