EXAONE 4.0 32B
EXAONE 4.0 32B is behind the leaders in agentic tasks. Too few results yet to rate reasoning, coding, safety, long context, math, multimodal tasks, multilingual tasks, instruction following, or factuality.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Reasoning, Coding, Safety, Long Context, Math, Multimodal, Multilingual, Instruction Following or Factuality.
Price
No current price is tracked for this model. See the rate card
Evidence
33results on19benchmarks
- 4 independently verified
- 29 aggregator
From 2 sources · latest Oct 8, 2026 · How verification works
EXAONE 4.0 32B benchmark results
33 results on 19 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
43.7% behind the leader1 of 7 ranked benchmarks measured
- 0.19Jun 15, 2026
Show 1 more agentic resultHide 1 agentic result
- 0.00Jun 15, 2026
0 of 6 ranked benchmarks measured
- 0.00Oct 8, 2026
- GPQA Diamond73.94Oct 8, 2026gpqa
- Humanity's Last Exam11.45Oct 8, 2026aa_hle
Show 2 more reasoning resultsHide 2 reasoning results
- GPQA Diamond62.83Oct 8, 2026gpqa
- Humanity's Last Exam5.00Oct 8, 2026aa_hle
0 of 10 ranked benchmarks measured
- Terminal-Bench Hard3.79Oct 8, 2026aa_terminalbench_hard
- Terminal-Bench Hard1.52Oct 8, 2026aa_terminalbench_hard
- SciCode34.38Sep 4, 2026aa_scicode
Show 1 more coding resultHide 1 coding result
- SciCode25.23Sep 4, 2026aa_scicode
0 of 3 ranked benchmarks measured
- 14.67Sep 4, 2026
- 9.00Sep 4, 2026
0 of 3 ranked benchmarks measured
0 of 4 ranked benchmarks measured
- AA-Omniscience · Accuracy13.87Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination14.16Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy10.62Oct 8, 2026omniscienceAccuracy
Show 1 more factuality resultHide 1 factuality result
- AA-Omniscience · Non-hallucination17.90Oct 8, 2026omniscienceNonHallucination
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- 56.29May 3, 2026
- 88.25May 3, 2026
- 98.84May 3, 2026
- 80.88May 3, 2026
- AA Intelligence8.18Oct 8, 2026aa_intelligence_index
- τ²-Bench Telecom (AA run)17.25Oct 8, 2026aa_tau2
Show 8 more resultsHide 8 results
- 9.53Jun 18, 2026
- 1.36Jun 18, 2026
- AA Intelligence6.33Oct 8, 2026aa_intelligence_index
- -60.07Oct 8, 2026
- -62.77Oct 8, 2026
- 9.42Jun 18, 2026
- 13.98Jun 18, 2026
- τ²-Bench Telecom (AA run)4.09Oct 8, 2026aa_tau2
EXAONE 4.0 32B: common questions
Who makes EXAONE 4.0 32B?
EXAONE 4.0 32B is made by LG AI.
When was EXAONE 4.0 32B released?
EXAONE 4.0 32B was released on Jul 15, 2025, according to Artificial Analysis.
What is EXAONE 4.0 32B good at?
EXAONE 4.0 32B is behind the leaders in agentic tasks. Too few results yet to rate reasoning, coding, safety, long context, math, multimodal tasks, multilingual tasks, instruction following, or factuality.
How many benchmarks has EXAONE 4.0 32B been tested on?
We track 33 results for EXAONE 4.0 32B on 19 benchmarks from 2 sources, 4 of them independently verified. The latest was recorded on Oct 8, 2026.
About this record
Where EXAONE 4.0 32B's numbers come from, and every name it appears under.
- Tracked since
- May 2, 2026
- Newest source mention
- Jul 20, 2026
Where the results come from
Verification: 33 scores · 4 independently verified · 29 aggregator-attributed. How these tiers are assigned
From 2 sources on 2 sites. Artificial Analysis supplies 29 of them; the 4 independently verified results come from 1 site. Bars are coloured by trust tier.
- artificialanalysis.ai29
- livecodebench.github.io4