Skip to main content

Model profile

Exaone 4.0 32B

LG AI ResearchTrackedKorea-market model
Data verified
Overall Score
40.44Public #170 of 200
Arena Elo
Not listed
Eligible category ranks
0of 8
Price (1M tokens)
Not listedAPI pricing
Speed
Not listed
Context
128K

Evidence coverage

13 of 323 tracked benchmarks are published. 2 are verified and 11 provisional. 6 of 8 categories are measured.

Updated July 23, 2026Methodology
Published / tracked
13 / 323
Verified
2
Provisional
11
Categories with evidence
6 / 8

Evidence by category

  • Agentic1 benchmark
    Reported
  • Coding1 benchmark
    Reported
  • Reasoning2 benchmarks
    Reported
  • Knowledge7 benchmarks
    Mixed evidence
  • Math1 benchmark
    Verified
  • Multilingual0 benchmarks
    Not measured
  • Multimodal0 benchmarks
    Not measured
  • Inst. Following1 benchmark
    Reported
Open WeightSelf-hostReasoning
Confidence:
Low
32b

BenchLM tracks Exaone 4.0 32B as a regional Korea model. Its benchmark rows are published for direct inspection, but it is intentionally excluded from the public global leaderboard so local-market scores do not skew worldwide rankings.

Exaone 4.0 32B is a open weight model with a 128K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

Exaone 4.0 32B sits inside the Exaone 4.0 family alongside Exaone 4.0 1.2B. This profile currently has 13 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 39.0648.45

  1. K-Exaone
    LG AI Research
    #12648.45
    K-Exaone is #126 with a score of 48.45.
    Compare
  2. Solar Pro 2
    Upstage
    #16741.19
    Solar Pro 2 is #167 with a score of 41.19.
    Compare
  3. Exaone 4.0 32BCurrent model
    LG AI Research
    #17040.44
    Exaone 4.0 32B is #170 with a score of 40.44.
  4. Exaone 4.0 1.2B
    LG AI Research
    #17939.06
    Exaone 4.0 1.2B is #179 with a score of 39.06.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

No eligible category percentile is available from the published evidence yet.

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticWeight 22%1 benchmarkReportedScore pending
CodingWeight 20%1 benchmarkReportedScore pending
ReasoningWeight 17%2 benchmarksReportedScore pending
KnowledgeRank Not rankedWeight 12%7 benchmarksMixed sources76.5
MathWeight 5%1 benchmarkVerifiedScore pending
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalWeight 12%0 benchmarksNot measuredNot measured
Inst. FollowingWeight 5%1 benchmarkReportedScore pending

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic1 benchmark
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

4.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Coding1 benchmark
AA-SciCodeReported

Artificial Analysis SciCode

25.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

8.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

0.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Knowledge7 benchmarks
MMLU-ProProvider exact

Massive Multitask Language Understanding Professional

81.8%Weighted 30%
Source: EXAONE 4.0 32B model cardProvenance: Provider exact
Artificial Analysis Intelligence IndexReported
6.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

62.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

4.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

-62.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

10.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

81.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Math1 benchmark
AIME 2025Provider exact

American Invitational Mathematics Examination 2025

85.3%Display only
Source: EXAONE 4.0 32B model cardProvenance: Provider exact
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

33.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.

Exaone 4.0 Family

32b

Frequently Asked Questions

How does Exaone 4.0 32B perform overall in AI benchmarks?

Exaone 4.0 32B is tracked as a regional Korea model on BenchLM. Its Korean benchmark scores are visible on the model profile and Korean leaderboards, but it is intentionally excluded from the global overall ranking so regional results do not distort worldwide comparisons.

Is Exaone 4.0 32B good for knowledge and understanding?

Exaone 4.0 32B has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is Exaone 4.0 32B good for coding and programming?

Exaone 4.0 32B has visible benchmark coverage in coding and programming, but BenchLM does not currently assign it a global category rank there.

Is Exaone 4.0 32B good for mathematics?

Exaone 4.0 32B has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.

Is Exaone 4.0 32B good for reasoning and logic?

Exaone 4.0 32B has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is Exaone 4.0 32B good for agentic tool use and computer tasks?

Exaone 4.0 32B has visible benchmark coverage in agentic tool use and computer tasks, but BenchLM does not currently assign it a global category rank there.

Is Exaone 4.0 32B good for instruction following?

Exaone 4.0 32B has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Is Exaone 4.0 32B open source?

Yes, Exaone 4.0 32B is an open weight model created by LG AI Research, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

Which sibling models are related to Exaone 4.0 32B?

Exaone 4.0 32B belongs to the Exaone 4.0 family. Related variants on BenchLM include Exaone 4.0 1.2B.

Does Exaone 4.0 32B have full benchmark coverage on BenchLM?

Not yet. Exaone 4.0 32B currently has 13 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Exaone 4.0 32B?

Exaone 4.0 32B has a published context window of 128K, which determines how much text it can process in a single interaction.

Last updated: July 23, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.