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
1224 models729 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

reasoning benchmark

ERQA Leaderboard

ERQA is a reasoning benchmark with 400 multiple-choice visual questions covering spatial reasoning, trajectory reasoning, action reasoning, state estimation, and multi-view reasoning.

Updated Sep 5, 2026

Models26
Model coverage26
MetricScore
EvidenceC

On this page

  • Ranking
  • Highlights
  • Distribution
  • Top models
  • About
  • FAQ

ERQA Ranking

Higher score ranks better on this benchmark.

26 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelACQwen3.8 MaxAlibaba Cloud / Qwen TeamScore77.80%Percentile100.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank02ModelACQwen3.8-Flash-NextAlibaba Cloud / Qwen TeamScore72.30%Percentile96.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank03ModelACQwen3.8 FlashAlibaba Cloud / Qwen TeamScore72.30%Percentile92.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank04ModelBYSeed 2.1 ProByteDanceScore72.00%Percentile88.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank05ModelBYSeed 2.1 TurboByteDanceScore71.30%Percentile84.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank06ModelACQwen3.7-PlusAlibaba Cloud / Qwen TeamScore69.80%Percentile80.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank07ModelOPGPT-5OpenAIScore65.70%Percentile76.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank08ModelACQwen3.6 PlusAlibaba Cloud / Qwen TeamScore65.70%Percentile72.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank09ModelACQwen3.8-27BAlibaba Cloud / Qwen TeamScore65.50%Percentile68.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank10ModelACQwen3.5-35B-A3BAlibaba Cloud / Qwen TeamScore64.80%Percentile64.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank11ModelMEMuse SparkMetaScore64.70%Percentile60.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank12ModelOPo3OpenAIScore64.00%Percentile56.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank13ModelACQwen3.6-27BAlibaba Cloud / Qwen TeamScore62.50%Percentile52.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank14ModelACQwen3.5-122B-A10BAlibaba Cloud / Qwen TeamScore62.00%Percentile48.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank15ModelACQwen3.5-27BAlibaba Cloud / Qwen TeamScore60.50%Percentile44.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank16ModelACQwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen TeamScore52.50%Percentile40.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank17ModelACQwen3 VL 32B ThinkingAlibaba Cloud / Qwen TeamScore52.30%Percentile36.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank18ModelACQwen3 VL 235B A22B InstructAlibaba Cloud / Qwen TeamScore51.30%Percentile32.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank19ModelACQwen3 VL 32B InstructAlibaba Cloud / Qwen TeamScore48.80%Percentile28.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank20ModelACQwen3 VL 4B ThinkingAlibaba Cloud / Qwen TeamScore47.30%Percentile24.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank21ModelACQwen3 VL 8B ThinkingAlibaba Cloud / Qwen TeamScore46.80%Percentile20.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank22ModelACQwen3 VL 8B InstructAlibaba Cloud / Qwen TeamScore45.80%Percentile16.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank23ModelACQwen3 VL 30B A3B ThinkingAlibaba Cloud / Qwen TeamScore45.30%Percentile12.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank24ModelACQwen3 VL 30B A3B InstructAlibaba Cloud / Qwen TeamScore43.00%Percentile8.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank25ModelACQwen3 VL 4B InstructAlibaba Cloud / Qwen TeamScore41.30%Percentile4.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank26ModelOPGPT-4oOpenAIScore35.20%Percentile0.00%Participants26EvidenceCEvaluatedSep 8, 2026

ERQA Highlights

The leading models and scores on this benchmark.

ERQA Score Distribution

A closer view of the leading scores on this benchmark.

ERQA

The Top AI Models for ERQA

The first five results on this benchmark, with official price and output speed added where the model identity can be matched.

What is ERQA?

What ERQA measures and how its scores work.

ERQA is an Embodied Reasoning Question Answering benchmark for evaluating AI capabilities in physical world interactions.

ERQA measures performance on spatial reasoning, trajectory reasoning, action reasoning, state estimation, and multi-view reasoning using a Score reported as a ratio.

Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of C.

Family
ERQA
Modality
multimodal
Primary category
reasoning
Score direction
higher
LLMBoard eligible
No
Evaluation key
overall

LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.

FAQ

Common questions about ERQA.

Which model scores highest on ERQA?

Qwen3.8 Max is currently ranked first with 77.80%.

What are the top three models on ERQA?

The current leaders are Qwen3.8 Max (77.80%), Qwen3.8-Flash-Next (72.30%), and Qwen3.8 Flash (72.30%).

Which ERQA model has the lowest official input price?

Qwen3.8 Flash has the lowest matched official input price at $0.15 input / $0.47 output per 1M tokens.

Which models are fastest among ERQA results?

The fastest matched records are GPT-4o (132.00 tok/s via OpenAI), GPT-5 (100.00 tok/s via OpenAI), and Qwen3.8 Max (60.87 tok/s via DeepInfra).

Does the highest score result prove overall model quality?

No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.

What does ERQA measure?

ERQA measures performance on spatial reasoning, trajectory reasoning, action reasoning, state estimation, and multi-view reasoning using a Score reported as a ratio.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

26 model results are currently shown.

Does this benchmark affect the overall score?

No. This benchmark is shown for reference but does not contribute to the overall score.

Rank #1Qwen3.8 Max77.80%
Rank #2Qwen3.8-Flash-Next72.30%
Rank #3Qwen3.8 Flash72.30%
Rank #4Seed 2.1 Pro72.00%

Ranking basisThis erqa AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    AC
    Qwen3.8 MaxAlibaba Cloud / Qwen Team
    Score
    77.80%
    Price
    $2.0 input / $6.0 output per 1M tokens
    Speed
    Up to 60.87 tok/s via DeepInfra

    Strengths

    • Ranks #1 of 26 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ERQA, not total model capability
  2. 02
    AC
    Qwen3.8-Flash-NextAlibaba Cloud / Qwen Team
    Score
    72.30%

    Strengths

    • Ranks #2 of 26 compared models
    • 96th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ERQA, not total model capability
  3. 03
    AC
    Alibaba Cloud / Qwen Team
    Score
    72.30%
    Price
    $0.15 input / $0.47 output per 1M tokens

    Strengths

    • Ranks #3 of 26 compared models
    • 92th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ERQA, not total model capability
  4. 04
    BY
    ByteDance
    Score
    72.00%

    Strengths

    • Ranks #4 of 26 compared models
    • 88th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ERQA, not total model capability
  5. 05
    BY
    ByteDance
    Score
    71.30%

    Strengths

    • Ranks #5 of 26 compared models
    • 84th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ERQA, not total model capability

Selection summary

Best AI Models for ERQA

Qwen3.8 Max currently leads ERQA with 77.80%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.

Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.

Qwen3.8 Flash
Seed 2.1 Pro
Seed 2.1 Turbo
Benchmark rank #1Qwen3.8 Max77.80% · $2.0 input / $6.0 output per 1M tokens
Benchmark rank #2Qwen3.8-Flash-Next72.30%
Benchmark rank #3Qwen3.8 Flash72.30% · $0.15 input / $0.47 output per 1M tokens