# Celeris-1.1 Decision vs Claude Haiku 5.5

> Side-by-side benchmark comparison for Celeris-1.1 Decision and Claude Haiku 5.5 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/celeris-1-1-decision-vs-claude-haiku-5-5
- Last updated: November 5, 2026

- Shared sourced benchmarks: 0
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

No benchmark verdict yet: there is no shared sourced benchmark row for Celeris-1.1 Decision and Claude Haiku 5.5.

## Summary

- Celeris-1.1 Decision and Claude Haiku 5.5 do not currently share a sourced benchmark row. The mirror therefore compares metadata, pricing, context windows, and each model's separately reported coverage without naming a benchmark winner.

## Model Snapshot

| Property | Celeris-1.1 Decision | Claude Haiku 5.5 |
|----------|----------|----------|
| Creator | Celeris | Anthropic |
| Type | Proprietary | Proprietary |
| Reasoning | Unspecified | Reasoning |
| Context | 131K | 1M |
| Independent public score (not head-to-head) | null | 66.56 |
| Benchmarks Covered | 0 | 19 |
| Pricing (input/output) | $0.04 / $0.00 | $0.10 / $0.50 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Celeris-1.1 Decision public-lane score: Coming soon
- Claude Haiku 5.5 public-lane score: 61.8 (Supported · #22/135)

| Benchmark | Celeris-1.1 Decision | Claude Haiku 5.5 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 4.0 | Coming soon | 39.20% | Coming soon |
| HLE w/ tools | Coming soon | 57.4% | Coming soon |
| MazeBench | Coming soon | 1% | Coming soon |
| Hermes Index | Coming soon | 37.0% | Coming soon |
| Hermes Bench | Coming soon | 71.0% | Coming soon |
| OSWorld 2.1 Offline | Coming soon | 72.4% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Celeris-1.1 Decision public-lane score: Coming soon
- Claude Haiku 5.5 public-lane score: 52.3 (Supported · #40/156)

| Benchmark | Celeris-1.1 Decision | Claude Haiku 5.5 | Winner |
|-----------|-----------|-----------|--------|
| FrontierCode 1.1 Main | Coming soon | 46.4% | Coming soon |
| Bug Hunt Bench | Coming soon | 21.5 fixes | Coming soon |
| FrontierSWE v2 | Coming soon | 43.8% | Coming soon |
| FrontierCode 2.0 | Coming soon | 27.7% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Celeris-1.1 Decision public-lane score: Coming soon
- Claude Haiku 5.5 public-lane score: 59.8 (#22/26)

| Benchmark | Celeris-1.1 Decision | Claude Haiku 5.5 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-1 | Coming soon | 89.00% | Coming soon |
| ARC-AGI-2 | Coming soon | 61.3% | Coming soon |
| ARC-AGI-3 | Coming soon | 0.5% | Coming soon |
| ARC-AGI-3 Provider Adapter | Coming soon | 2.82% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Celeris-1.1 Decision public-lane score: Coming soon
- Claude Haiku 5.5 public-lane score: Coming soon

| Benchmark | Celeris-1.1 Decision | Claude Haiku 5.5 | Winner |
|-----------|-----------|-----------|--------|
| ParseBench | Coming soon | 56.02% | Coming soon |
| Chartography (no tools) | Coming soon | 46.4% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Celeris-1.1 Decision public-lane score: Coming soon
- Claude Haiku 5.5 public-lane score: 65.3 (Supported · #30/177)

| Benchmark | Celeris-1.1 Decision | Claude Haiku 5.5 | Winner |
|-----------|-----------|-----------|--------|
| HLE w/o tools | Coming soon | 45.9% | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Celeris-1.1 Decision public-lane score: Coming soon
- Claude Haiku 5.5 public-lane score: 79.1 (Unranked · 2 rankable rows)

| Benchmark | Celeris-1.1 Decision | Claude Haiku 5.5 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | Coming soon | 75.088% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 46.341% | Coming soon |

## FAQ

### Can I compare Celeris-1.1 Decision and Claude Haiku 5.5 on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but sourced benchmark coverage is still incomplete for a fair score-level comparison.

### Why does this page show "coming soon" values?

BenchLM only calls winners when public benchmark coverage is available on both sides of the comparison.

## Related Comparisons

- [Celeris-1.1 Decision vs Celeris-1 Decision](/compare/celeris-1-1-decision-vs-celeris-1-decision)
- [Claude Haiku 5.5 vs Celeris-1 Decision](/compare/celeris-1-decision-vs-claude-haiku-5-5)
- [Celeris-1.1 Decision vs Gemini 4 Carbon](/compare/celeris-1-1-decision-vs-gemini-4-carbon)
- [Claude Haiku 5.5 vs Gemini 4 Carbon](/compare/claude-haiku-5-5-vs-gemini-4-carbon)

## Explore More

- [Celeris-1.1 Decision profile](/models/celeris-1-1-decision)
- [Claude Haiku 5.5 profile](/models/claude-haiku-5-5)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)