# Sage-A1.5 Benchmark Scores & Performance

> Sage-A1.5 by InternScience scores 62.95/100 overall, ranking #44 out of 989 AI models.

Canonical page: https://benchlm.ai/models/sage-a1-5

Last updated: October 20, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | InternScience |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 262K |
| Official model card | [InternScience Sage-A1.5 model card](https://huggingface.co/InternScience/Sage-A1.5) |
| Overall Score | 62.95/100 |
| Overall Rank | #44 of 989 |

## Family & Coverage

- Family: Sage-A1.5
- Variant: base
- Benchmarks covered: 13 of 670
- Sibling models: [Sage-A1.5-F16-GGUF](/models/sage-a1-5-f16-gguf), [Sage-A1.5-FP8](/models/sage-a1-5-fp8), [Sage-A1.5-Q4_K_M-GGUF](/models/sage-a1-5-q4-k-m-gguf), [Sage-A1.5-Q8_0-GGUF](/models/sage-a1-5-q8-0-gguf)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [GAIA](/benchmarks/gaia) | 95.1% | [InternScience Sage-A1.5 model card](https://huggingface.co/InternScience/Sage-A1.5) |
| [BrowseComp](/benchmarks/browsecomp) | 81.7% | [InternScience Sage-A1.5 model card](https://huggingface.co/InternScience/Sage-A1.5) |
| [MLE-Bench Lite](/benchmarks/mle-bench-lite) | 65.2% | [InternScience Sage-A1.5 model card](https://huggingface.co/InternScience/Sage-A1.5) |
| [HLE w/ tools](/benchmarks/hlewithtools) | 55.1% | [InternScience Sage-A1.5 model card](https://huggingface.co/InternScience/Sage-A1.5) |
| [VITA-Bench](/benchmarks/vitabench) | 45.4% | [InternScience Sage-A1.5 model card](https://huggingface.co/InternScience/Sage-A1.5) |
| [PinchBench](/benchmarks/pinchbench) | 90.0% | [InternScience Sage-A1.5 model card](https://huggingface.co/InternScience/Sage-A1.5) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [SciCode](/benchmarks/scicode) | 44.3% | [InternScience Sage-A1.5 model card](https://huggingface.co/InternScience/Sage-A1.5) |
| [SWE-bench Pro](/benchmarks/swe-bench-pro) | 61.2% | [InternScience Sage-A1.5 model card](https://huggingface.co/InternScience/Sage-A1.5) |
| [SWE Multilingual](/benchmarks/swe-bench-multilingual) | 72.7% | [InternScience Sage-A1.5 model card](https://huggingface.co/InternScience/Sage-A1.5) |

## Reasoning Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AA-LCR](/benchmarks/lcr) | 81.0% | [InternScience Sage-A1.5 model card](https://huggingface.co/InternScience/Sage-A1.5) |
| [CritPt](/benchmarks/critpt) | 20.0% | [InternScience Sage-A1.5 model card](https://huggingface.co/InternScience/Sage-A1.5) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [FrontierScience Research](/benchmarks/frontierscienceresearch) | 48.3% | [InternScience Sage-A1.5 model card](https://huggingface.co/InternScience/Sage-A1.5) |

## Instruction Following Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [IFBench](/benchmarks/ifbench) | 81.6% | [InternScience Sage-A1.5 model card](https://huggingface.co/InternScience/Sage-A1.5) |

## Other InternScience Models

- [Agents-A1](/models/agents-a1) - Score: 54.37
- [Agents-A1-F16-GGUF](/models/agents-a1-f16-gguf) - Score: 54.37
- [Agents-A1-FP8](/models/agents-a1-fp8) - Score: 54.37
- [Agents-A1-Q4_K_M-GGUF](/models/agents-a1-q4-k-m-gguf) - Score: 54.37
- [Agents-A1-Q8_0-GGUF](/models/agents-a1-q8-0-gguf) - Score: 54.37
- [Agents-A1-4B](/models/agents-a1-4b) - Score: not computed
- [Sage-A1.5-F16-GGUF](/models/sage-a1-5-f16-gguf) - Score: not computed
- [Sage-A1.5-FP8](/models/sage-a1-5-fp8) - Score: not computed
- [Sage-A1.5-Q4_K_M-GGUF](/models/sage-a1-5-q4-k-m-gguf) - Score: not computed
- [Sage-A1.5-Q8_0-GGUF](/models/sage-a1-5-q8-0-gguf) - Score: not computed