What are Solar Open 100B's benchmark scores?

As of 25 Oct 2026, Solar Open 100B (thinking effort) scores 45.3 ±5.9 on the BenchLeader Index, strongest in instruction following (58) and weakest in agents & tools (36). That rests on 6 independent benchmark results, and every score on this page links to its publisher.

How does Solar Open 100B rank?

Solar Open 100B (thinking effort) is #521 of 785 ranked configurations on 25 Oct 2026. 355 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

When was Solar Open 100B released?

Upstage released Solar Open 100B on 17 Dec 2025.

Upstage Open weights: upstage/Solar-Open-100BReasoning modelCompare with another model

Solar Open 100B

Solar Open 100B is an Upstage open-weights reasoning model, released 17 Dec 2025. Its best configuration (thinking reasoning effort) ranks #521 of 785 on the BenchLeader Index at 45.3 ±5.9, in the lower half. The ± is the point: 355 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (58) and lowest in agents & tools (36). Last measured 17 Dec 2025.stale: no new result in six months

Blended price: –
Output speed: –
First answer: –
Context: 128k
Full answer: –
Cost per run: –
Released: 17 Dec 2025

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index45
Reasoning41
Agents & tools36
Knowledge37
Instruction following58
Long context45
Composite41

How its index has moved

9 Sept 2026 to 21 Oct 2026

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	thinking	Source
GPQA Diamond (AA)not in index	65.7%#339	Artificial Analysis
Humanity's Last Exam (AA)not in index	10.4%#317	Artificial Analysis
CritPt	0.0%#315	Artificial Analysis

Agents & tools

Benchmark	thinking	Source
Terminal-Bench Hard	2.3%#320	Artificial Analysis
τ²-Bench Telecom (AA)not in index	48.3%#201	Artificial Analysis

Knowledge

Benchmark	thinking	Source
AA-Omniscience	-54.5#429	Artificial Analysis
AA-Omniscience: accuracynot in index	18.5%#333	Artificial Analysis
AA-Omniscience: non-hallucinationnot in index	10.3%#410	Artificial Analysis

Instruction following

Benchmark	thinking	Source
IFBench	57.7%#137	Artificial Analysis

Long context

Benchmark	thinking	Source
AA-LCR	41.0%#356	Artificial Analysis

Composite

Benchmark	thinking	Source
AA Intelligence Index v4.3.2	10.4#377	Artificial Analysis

New this month

Questions people ask

What are Solar Open 100B's benchmark scores?: As of 25 Oct 2026, Solar Open 100B (thinking effort) scores 45.3 ±5.9 on the BenchLeader Index, strongest in instruction following (58) and weakest in agents & tools (36). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
How does Solar Open 100B rank?: Solar Open 100B (thinking effort) is #521 of 785 ranked configurations on 25 Oct 2026. 355 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
When was Solar Open 100B released?: Upstage released Solar Open 100B on 17 Dec 2025.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Solar Open 100B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/solar-open-100b.