Inference
EN
InternScience

Sage-A1.5

Sage-A1.5 is a reasoning model from InternScience. 9 benchmarks count toward its index, in 4 categories.

  • Open weights
  • Reasoning
  • Input: text
  • Released 2026-10
RankedEnough results for an index.
IndexAll categories, out of 100.60.5±9.4Median 51.0
CoverageIndex weight that has results.60%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.262KMedian 262K
EloLMArena rating and rank.—Median 1422

Run locally

35.51B parameters
16-bit
75.6 GB
8-bit
40.6 GB
4-bit
23.6 GB
Weights
Hugging Face (opens in a new tab) ↗

Memory need with a short context. The 4-bit copy fits in 24 GB. Compare local models

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.4 counted59.474 / 218
CodingCode writing and repair.2 counted57.382 / 209
ReasoningLogic problems and puzzles.2 counted69.222 / 227
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.None counted——
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted65.3—
MathMath problems.None counted——

Results

9 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Instruction Following BenchmarkInstruction81.6%6 / 57
Critical Physics TasksReasoning20.0%30 / 214
Artificial Analysis Long Context ReasoningReasoning81.0%35 / 217
VITA-BenchAgentic45.4%3 / 13
PinchBenchAgentic90.0%3 / 10
SWE-bench ProCoding61.2%30 / 83
BrowseCompAgentic81.7%28 / 63
Scientific Code BenchmarkCoding44.3%16 / 35
Humanity's Last Exam with toolsAgentic55.1%20 / 36
General AI AssistantsAgentic95.1%—
MLE-Bench LiteAgentic65.2%—
FrontierScience ResearchKnowledge48.3%—

Sources

BenchLMCC BY-NC 4.0

History

5 releases
Index61.5 → 60.5
23 Oct 202612 Nov 2026

Questions

How good is Sage-A1.5?
Its index is 60.5 out of 100. That is place 69 of 283 ranked models.
What is Sage-A1.5 best at?
Reasoning: 69.2 out of 100, place 22 of 227.
What is the context window of Sage-A1.5?
262K tokens.
Is Sage-A1.5 open source?
Yes. Its weights are published.
When was Sage-A1.5 released?
October 2026.

Badge

Sage-A1.5 on Inference360: place 69 of 283, index 60.5
HTML
<a href="https://inference360.ai/models/sage-a1-5"><img src="https://inference360.ai/badges/sage-a1-5.svg" alt="Sage-A1.5 on Inference360: place 69 of 283, index 60.5" height="20"></a>
Markdown
[![Sage-A1.5 on Inference360: place 69 of 283, index 60.5](https://inference360.ai/badges/sage-a1-5.svg)](https://inference360.ai/models/sage-a1-5)

Compare with

Qwen3.7 Max60.5GLM-5.260.6Beam 1.0 501B-A23B60.2Agents-A1-4B46.8

More from InternScience

All models
Sage-A1.5-F16-GGUFUnrankedSage-A1.5-FP8UnrankedSage-A1.5-Q4_K_M-GGUFUnrankedSage-A1.5-Q8_0-GGUFUnrankedAgents-A1-4B46.8