all the models — AI benchmark observatory
← Models

Seed 1.8

ByteDance · proprietary · seed-1.8

Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.

LiveCodeBencCountBenchSimpleVQARefSpatialBeZEROBenchAIME 2025

Benchmark scores

BenchmarkScore
LiveCodeBench Pro1930.00
CountBench96.30
SimpleVQA65.40
RefSpatialBench56.30
ZEROBench11.00
AIME 20250.94
VLMsAreBlind0.93
MMLU0.92
AI2D0.89
VideoMME w sub.0.88
MathVista0.88
TempCompass0.87
MMLU-Pro0.85
MMMU0.83
MMMU-Pro0.73
SWE-Bench Verified0.73

Pricing

  • DeepInfra$0.25 / $2.00

Input / output per 1M tokens

AA metrics

No Artificial Analysis link yet.

Arena Elo

  • No Arena snapshot linked.