EXAONE 4.5 33B
EXAONE 4.5 33B is behind the leaders in multimodal tasks, long context, instruction following, coding, and reasoning. Too few results yet to rate agentic tasks, safety, math, multilingual tasks, 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 Agentic, Safety, Math, Multilingual or Factuality.
Price
No current price is tracked for this model. See the rate card
Evidence
32results on29benchmarks
- 18 aggregator
- 14 vendor-reported
From 2 sources · latest Oct 8, 2026 · How verification works
EXAONE 4.5 33B benchmark results
32 results on 29 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
25.3% behind the leader3 of 6 ranked benchmarks measured
34.3% behind the leader1 of 3 ranked benchmarks measured
- 54.67Oct 8, 2026
Show 1 more long context resultHide 1 long context result
- 50.60Oct 7, 2026
34.6% behind the leader1 of 3 ranked benchmarks measured
- IFBench57.96Oct 8, 2026aa_ifbench
40.3% behind the leader4 of 10 ranked benchmarks measured
- 81.40Oct 7, 2026
- SciCode28.01Sep 4, 2026aa_scicode
- Terminal-Bench Hard20.45Oct 8, 2026aa_terminalbench_hard
- Terminal-Bench 2.121.35Oct 8, 2026terminalbenchV21
41.1% behind the leader3 of 6 ranked benchmarks measured
- GPQA Diamond79.39Oct 8, 2026gpqa
- Humanity's Last Exam12.88Oct 8, 2026aa_hle
- 0.29Oct 8, 2026
Show 1 more reasoning resultHide 1 reasoning result
- GPQA Diamond80.50Oct 7, 2026GPQA
0 of 7 ranked benchmarks measured
- 0.00Oct 8, 2026
- τ-Bench V3 · Banking11.13Aug 10, 2026tauBanking
0 of 5 ranked benchmarks measured
- 92.60Oct 7, 2026
0 of 4 ranked benchmarks measured
- AA-Omniscience · Accuracy16.23Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination20.08Oct 8, 2026omniscienceNonHallucination
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- AA Intelligence13.21Oct 8, 2026aa_intelligence_index
- τ²-Bench Telecom (AA run)78.07Oct 8, 2026aa_tau2
- -50.72Oct 8, 2026
- Artificial Analysis Coding Index23.57Sep 9, 2026aa_coding_index
- 9.73Aug 10, 2026
- 89.00Oct 7, 2026
Show 5 more resultsHide 5 results
- 92.90Oct 7, 2026
- 89.60Aug 31, 2026
- 83.30Oct 7, 2026
- 56.50Oct 7, 2026
- τ²-Bench (Retail)77.90Oct 7, 2026Tau2 Retail
EXAONE 4.5 33B: common questions
Who makes EXAONE 4.5 33B?
EXAONE 4.5 33B is made by LG AI.
When was EXAONE 4.5 33B released?
EXAONE 4.5 33B was released on Apr 9, 2026, according to Artificial Analysis.
What is EXAONE 4.5 33B good at?
EXAONE 4.5 33B is behind the leaders in multimodal tasks, long context, instruction following, coding, and reasoning. Too few results yet to rate agentic tasks, safety, math, multilingual tasks, or factuality.
How many benchmarks has EXAONE 4.5 33B been tested on?
We track 32 results for EXAONE 4.5 33B on 29 benchmarks from 2 sources. The latest was recorded on Oct 8, 2026.
About this record
Where EXAONE 4.5 33B's numbers come from, and every name it appears under.
- Tracked since
- May 2, 2026
- Newest source mention
- May 2, 2026
Where the results come from
Verification: 32 scores · 0 independently verified · 18 aggregator-attributed · 14 vendor-reported. How these tiers are assigned
From 2 sources on 2 sites. Artificial Analysis supplies 18 of them. Bars are coloured by trust tier.
- artificialanalysis.ai18
- api.llm-stats.com14