LLM Leaderboard · Proprietary

Gemini 3.5 Flash leaderboard — benchmarks, pricing, and comparisons.

Compare Gemini 3.5 Flash vs GPT, Claude, Gemini, DeepSeek, open-weight, and frontier AI models using public benchmark scores, token pricing, context window, and access details.

Rank #20AskClash overall score: 55.5
$1.50 / $9.00Input and output token price, when published. Context: 1M.
Visit websiteVisit the model provider's website.

Gemini 3.5 Flash benchmark snapshot

AskClash combines public LLM benchmark cells into a weighted percentile score and penalizes missing coverage so narrow rows do not dominate better-measured models.

Overall55.5
Benchmark cells14
Context1M
CreatorGoogle

Gemini 3.5 Flash public benchmark scores

Cached benchmark values can include HLE, GPQA, SWE-bench, SWE-Pro, SWE-Atlas, Terminal-Bench, MCP Atlas, MMMU-Pro, ARC-AGI-2, Tau2, and model-specific coding or agent scores.

RWT

7.0 score

HLE

40.2 score

GPQA

92.2 score

IFEval

76.3 score

SWE-Pro

55.1 score

Terminal-Bench

76.2 score

OSWorld

78.4 score

MCP Atlas

83.6 score

Finance Agent

57.9 score

CharXiv

84.2 score

MMMU-Pro

83.6 score

ARC-AGI 2

72.1 score

Tau2

95.3 score

MRCR

77.3 score

Gemini 3.5 Flash vs other AI models

Use these comparison links to evaluate Gemini 3.5 Flash against nearby LLMs by benchmark score, price, context window, and provider.

Related AI and tech coverage

Cached AskClash article matches that can provide release, provider, benchmark, pricing, or market context around this model.

Vespa Newsletter, February 2026

Vespa Newsletter, February 2026 | Vespa Blog { } Blog Vespa.ai Docs Subscribe Vespa Blog We Make AI Work Share Bonnie Chase Director of Product Marketing 16 Feb 2026 Vespa Newsletter, February 2026 Welcome to the latest edition of the Vespa newsletter. In the previous update , we introduced several new features and improvements, including Automated ANN Tuning, Accelerated Exact Vector Distance with Google Highway, Precise Chunk-Level Matching for Higher Retrieval Quality, Quantile Computation in

Using Large ONNX Models with External Data in Vespa Embedders

Using Large ONNX Models with External Data in Vespa Embedders | Vespa Blog { } Blog Vespa.ai Docs Subscribe Vespa Blog We Make AI Work Share Bjørn C Seime Sr Principal Software Engineer Thomas H. Thoresen Principal Software Engineer 27 Mar 2026 Using Large ONNX Models with External Data in Vespa Embedders Many popular ONNX models exceed the 2 GB protobuf format limit and store their weights in separate external data files. Until recently, these models could not be used directly in Vespa’s built-

Last cached leaderboard date: July 8, 2026. This model page is generated from the AskClash LLM Leaderboard cache and linked from the live leaderboard.