LLM Leaderboard · Proprietary

Gemini 4 Neon benchmarks — leaderboard rank, pricing, and comparisons.

Gemini 4 Neon ranks #17 on the AskClash LLM leaderboard with an overall score of 59.1. It scores 61.6 on Terminal-Bench 4.0. Compare Gemini 4 Neon vs GPT, Claude, Gemini, DeepSeek, open-weight, and frontier AI models using public benchmark scores, token pricing, context window, and access details.

Rank #17AskClash overall score: 59.1
$3.00 / $15.0Input and output token price, when published. Context: 1M.
Visit websiteVisit the model provider's website.

Gemini 4 Neon 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.

Overall59.1
Benchmark cells5
Context1M
CreatorGoogle

Gemini 4 Neon 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.

AA Intelligence Index

59.6 score

AutomationBench-AA

79.2 score

SWE-Atlas

67.7 score

Terminal-Bench 4.0

61.6 score

Finance Agent v2.1

68.6 score

More published benchmark results

Results are grouped by evaluator, benchmark version, and effort where published.

Artificial Analysis High

  • HLE-Diamond: 68.4%
  • FrontierCode-AA 2.0: 43.28%
  • GDP.pdf all-pass: 33.4%
  • Terminal-Bench-Science 0.1: 65.71%
  • CritPt v2 hard subset: 59.0%

Artificial Analysis XHigh

  • AA Intelligence Index v5.0.1: 61.40
  • AA-Briefcase v1.1: 1,700 Elo
  • HLE-Diamond: 71.3%
  • Terminal-Bench 4.0: 63.64%

Google model card

  • CursorBench 4.1: 65.4%
  • Terminal-Bench 4.1 (cheating-adjusted): 65.2%
  • FrontierCode 2.0: 46.2%
  • SWE-sweep (provider harness): 39.0%
  • SWE-sweep (Mini-SWE harness): 12.8%
  • AutomationBench (Zapier): 56.3%
  • Agents' Last Exam v1.1: 75.8%
  • RiemannBench: 84.0%
  • Terminal-Bench-Science 0.1: 70.5%
  • Multimodal Knowledge Agent (Climb WSR): 56.5%
  • Chartography: 73.5%
  • LVBench: 89.0%
  • GraphWalks 256k–1M BFS F1: 95.2%
  • CWE-Bench v2: 70.7%
  • SEC-bench Pro: 90.5%
  • WebExploitBench v1.2: 51.3%

Google launch announcement

  • Agent Arena Index: 1,336
  • Vending-Bench 2 final balance: $16,843
  • Coding Agent Index v2.1 (Antigravity CLI, XHigh): 58.6

Vals AI (XHigh)

  • Vals Index v2.2: 70.87%
  • Vals Finance Index: 68.31%
  • Vals Legal Index: 78.36%
  • Vals Science Index: 62.63%
  • MysteryMechanism: 45.05%
  • EMB v1.1: 76.46%
  • Finance Agent v2.1: 68.56%
  • Legal Research Bench: 56.25%
  • Tax Agent Bench: 54.89%
  • Vibe Code Bench v1.1: 93.70%
  • BioMysteryBench: 80.00%
  • HLAB-Vals-1.1: 19.58%
  • Terminal-Bench 4.0: 61.62%
  • Terminal-Bench-Science: 62.86%

Gemini 4 Neon vs other AI models

Use these comparison links to evaluate Gemini 4 Neon 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.

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