# Agents-A1 vs Celeris-1

> Side-by-side benchmark comparison for Agents-A1 and Celeris-1 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/agents-a1-vs-celeris-1
- Last updated: September 4, 2026

- Shared sourced benchmarks: 1
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Evidence is too thin for a benchmark verdict: Agents-A1 and Celeris-1 share only 1 sourced benchmark row.

## Summary

- Only 1 shared sourced benchmark row is available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Agents-A1 has the larger published context window at 262K.

## Model Snapshot

| Property | Agents-A1 | Celeris-1 |
|----------|----------|----------|
| Creator | InternScience | Celeris |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Non-Reasoning |
| Context | 262K | 128K |
| Independent public score (not head-to-head) | null | null |
| Benchmarks Covered | 6 | 4 |
| Pricing (input/output) | N/A | $0.20 / $0.70 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Agents-A1 public-lane score: 52 (Estimated · #47/151)
- Celeris-1 public-lane score: Coming soon

| Benchmark | Agents-A1 | Celeris-1 | Winner |
|-----------|-----------|-----------|--------|
| BrowseComp | 75.5% | Coming soon | Coming soon |
| HLE w/ tools | 47.6% | Coming soon | Coming soon |
| VITA-Bench | 38.8% | Coming soon | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Agents-A1 public-lane score: 34.1 (Unranked · 1 rankable row)
- Celeris-1 public-lane score: 47.8 (Unranked · 3 rankable rows)

| Benchmark | Agents-A1 | Celeris-1 | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 60.2% | Coming soon | Coming soon |
| DROP | Coming soon | 81.4% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Agents-A1 public-lane score: 52.6 (Estimated · #73/181)
- Celeris-1 public-lane score: Coming soon

| Benchmark | Agents-A1 | Celeris-1 | Winner |
|-----------|-----------|-----------|--------|
| HLE | 47.6% | Coming soon | Coming soon |
| MMLU-Pro | Coming soon | 75.9% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Agents-A1 public-lane score: Coming soon
- Celeris-1 public-lane score: Coming soon

| Benchmark | Agents-A1 | Celeris-1 | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 94.8% | 80.8% | Agents-A1 |

### Mathematics

- Winner: Insufficient shared evidence
- Agents-A1 public-lane score: Coming soon
- Celeris-1 public-lane score: Coming soon

| Benchmark | Agents-A1 | Celeris-1 | Winner |
|-----------|-----------|-----------|--------|
| GSM8K | Coming soon | 93.7% | Coming soon |

## FAQ

### Is there enough evidence to pick between Agents-A1 and Celeris-1?

Not yet. The models share only 1 sourced benchmark row, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Agents-A1 vs Agents-A1-F16-GGUF](/compare/agents-a1-vs-agents-a1-f16-gguf)
- [Celeris-1 vs Agents-A1-F16-GGUF](/compare/agents-a1-f16-gguf-vs-celeris-1)
- [Agents-A1 vs Agents-A1-FP8](/compare/agents-a1-vs-agents-a1-fp8)
- [Celeris-1 vs Agents-A1-FP8](/compare/agents-a1-fp8-vs-celeris-1)

## Explore More

- [Agents-A1 profile](/models/agents-a1)
- [Celeris-1 profile](/models/celeris-1)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)