Model comparison
Celeris-1 vs Exaone 4.0 32B
Head-to-head evidence from 1 shared benchmark result across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Celeris-1 unranked (Not scored); Exaone 4.0 32B #170 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Celeris-1 and Exaone 4.0 32B share 1 comparable benchmark result. 1 of 8 categories are comparable. 0 results are unique to Celeris-1; 12 to Exaone 4.0 32B.
Updated July 24, 2026- Shared results
- 1
- Celeris-1 only
- 0
- Exaone 4.0 32B only
- 12
- Comparable categories
- 1 / 8
Treat this as a split decision. Celeris-1 makes more sense if you would rather avoid the extra latency and token burn of a reasoning model; Exaone 4.0 32B is the better fit if knowledge is the priority or you need the larger 128K context window.
Confidence note. This is a partial-evidence comparison with 1 shared benchmark result across 1 evidence category; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Celeris-1 and Exaone 4.0 32B finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.
Exaone 4.0 32B is the reasoning model in the pair, while Celeris-1 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Exaone 4.0 32B gives you the larger context window at 128K, compared with 8K for Celeris-1.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Celeris-1 | Δ | Exaone 4.0 32B |
|---|---|---|---|
| Knowledge | Celeris-175.9 | Margin→ 5.9 | Exaone 4.0 32B81.8 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
MMLU-Pro
KnowledgeA 75.9%B 81.8%Winner: Exaone 4.0 32BΔ 5.9MMLU-Pro: Celeris-1 scored 75.9%; Exaone 4.0 32B scored 81.8%. Exaone 4.0 32B wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Celeris-1 | Exaone 4.0 32B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Celeris-1$2 input / $6 output | Exaone 4.0 32BNot available | A complete price comparison is not available. |
| Generation speedtokens per second | Celeris-1Not available | Exaone 4.0 32BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Celeris-1Not available | Exaone 4.0 32BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Celeris-18K | Exaone 4.0 32B128K | Exaone 4.0 32B lists the larger context window. |
Benchmark Deep Dive
Agentic1 benchmarks
| Benchmark | Celeris-1 | Exaone 4.0 32B | Result |
|---|---|---|---|
| τ²-bench resultsSource | — | 4.1% | Not comparable |
Coding1 benchmarks
| Benchmark | Celeris-1 | Exaone 4.0 32B | Result |
|---|---|---|---|
| AA-SciCodeSource | — | 25.2% | Not comparable |
Reasoning2 benchmarks
KnowledgeExaone 4.0 32B wins7 benchmarks
| Benchmark | Celeris-1 | Exaone 4.0 32B | Result |
|---|---|---|---|
| MMLU-ProSource | 75.9% | 81.8% | Exaone 4.0 32B leads |
| Artificial Analysis Intelligence IndexSource | — | 6.0% | Not comparable |
| AA-GPQA DiamondSource | — | 62.8% | Not comparable |
| AA-HLESource | — | 4.9% | Not comparable |
| AA-Omniscience IndexSource | — | -62.3% | Not comparable |
| AA-Omniscience AccuracySource | — | 10.4% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 81.0% | Not comparable |
Math1 benchmarks
| Benchmark | Celeris-1 | Exaone 4.0 32B | Result |
|---|---|---|---|
| AIME 2025Source | — | 85.3% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Celeris-1 | Exaone 4.0 32B | Result |
|---|---|---|---|
| AA-IFBenchSource | — | 33.5% | Not comparable |
Frequently Asked Questions (2)
Which is better, Celeris-1 or Exaone 4.0 32B?
Celeris-1 and Exaone 4.0 32B are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.
Which is better for knowledge tasks, Celeris-1 or Exaone 4.0 32B?
Exaone 4.0 32B has the edge for knowledge tasks in this comparison, averaging 81.8 versus 75.9. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.