ModelBench

Gemini 3.5 Flash Lite vs GPT-5.6 Luna vs Laguna S 2.1

Compare Gemini 3.5 Flash Lite and GPT-5.6 Luna and Laguna S 2.1 on key metrics including pricing, context length, capabilities, providers, and published benchmarks.

3 of 6 selected
Clear all

Overview

Author Google
Context length 1.04858Mtokens
Reasoning Supported
Input modalities T
Output modalities T
Providers 24 providers
Author OpenAI
Context length 1.05MtokensBest
Reasoning Supported
Input modalities T
Output modalities T
Providers 37 providers
Author Poolside
Context length 1.04858Mtokens
Reasoning Supported
Input modalities T
Output modalities T
Providers 7 providers

Pricing per million tokens

Input $0.3
Output $2.5
Cached input $0.03
Cache write Not listed
Input $0.2
Output $1.2
Cached input $0.02
Cache write $0.25
Input $0.09Best
Output $0.18Best
Cached input $0.009
Cache write Not listed

Limits

Context length 1.04858Mtokens
Max output 65.536Ktokens
Released 2026-07-21
Knowledge cutoff 2026-03
Context length 1.05MtokensBest
Max output 128KtokensBest
Released 2026-07-09
Knowledge cutoff 2026-02-16
Context length 1.04858Mtokens
Max output 32.768Ktokens
Released 2026-07-21
Knowledge cutoff Not documented

Capabilities

Tool calling Supported
Structured output Supported
Vision input Supported
Attachments Supported
Tool calling Supported
Structured output Supported
Vision input Supported
Attachments Supported
Tool calling Supported
Structured output Not supported
Vision input Not supported
Attachments Not supported

Availability

Inference providers 24providers
Provider list 302aiGoogleabacuscortecscrossmodel+17 more
Inference providers 37providersBest
Provider list 302aiOpenAIabacusai-routeraihubmix+31 more
Inference providers 7providers
Provider list kilonano-gptopenrouterpioneerpoolside+1 more

Benchmarks

Intelligence index
0 27.5 55 claude-opus-4… — 55 index 55 claude-opus-4… claude-opus-4… — 55 index 55 claude-opus-4… claude-fable-… — 53.4 index 53.4 claude-fable-… claude-fable-… — 53.4 index 53.4 claude-fable-… qwen3.8-max — 53.4 index 53.4 qwen3.8-max gpt-5.4:batch — 53.1 index 53.1 gpt-5.4:batch gpt-5.4 — 53.1 index 53.1 gpt-5.4 gpt-6-astra:b… — 52.8 index 52.8 gpt-6-astra:b… Gemini 3.5 Fl… — 22.7 index 22.7 Gemini 3.5 Fl… GPT-5.6 Luna — 37.5 index 37.5 GPT-5.6 Luna
  • Gemini 3.5 Flash Lite
  • GPT-5.6 Luna

* Laguna S 2.1 has no intelligence data

Coding index
0 40.8 81.6 claude-fable-… — 81.6 index 81.6 claude-fable-… claude-fable-… — 81.6 index 81.6 claude-fable-… claude-opus-5… — 78 index 78 claude-opus-5… claude-opus-5 — 78 index 78 claude-opus-5 gpt-5.6-sol:b… — 77.4 index 77.4 gpt-5.6-sol:b… gpt-5.6-sol — 77.4 index 77.4 gpt-5.6-sol gpt-6-astra:b… — 76.9 index 76.9 gpt-6-astra:b… gpt-6-astra — 76.9 index 76.9 gpt-6-astra Gemini 3.5 Fl… — 49.3 index 49.3 Gemini 3.5 Fl… GPT-5.6 Luna — 71.4 index 71.4 GPT-5.6 Luna
  • Gemini 3.5 Flash Lite
  • GPT-5.6 Luna

* Laguna S 2.1 has no coding data

Agentic index
0 29 58 claude-fable-… — 58 index 58 claude-fable-… claude-fable-… — 58 index 58 claude-fable-… claude-opus-5… — 56.2 index 56.2 claude-opus-5… claude-opus-5 — 56.2 index 56.2 claude-opus-5 glm-5.3:batch — 53.4 index 53.4 glm-5.3:batch glm-5.3 — 53.4 index 53.4 glm-5.3 grok-4.6 — 53.4 index 53.4 grok-4.6 gpt-6-astra:b… — 51.5 index 51.5 gpt-6-astra:b… Gemini 3.5 Fl… — 15.9 index 15.9 Gemini 3.5 Fl… GPT-5.6 Luna — 42.7 index 42.7 GPT-5.6 Luna
  • Gemini 3.5 Flash Lite
  • GPT-5.6 Luna

* Laguna S 2.1 has no agentic data

All published benchmark results 21 variants
Agentic Index index15.9
Agents' Last Exam scoreNot reported
Artificial Analysis Coding Agent Index index score · 1.1 · CodexNot reported
Artificial Analysis Intelligence Index index score · 4.1Not reported
BrowseComp accuracyNot reported
CharXiv Reasoning accuracy76.5Best
Coding Index index49.3
DeepSWE resolve rate · 1.1Not reported
FrontierMath accuracy · v2Not reported
GDM-MRCR accuracy · v221.3Best
GDPval-AA Elo · v21140.0Best
GPQA Diamond accuracyNot reported
Intelligence Index index22.7
MLE-Bench average position score39.2Best
MMMU Pro accuracyNot reported
OSWorld success rate · 2.0Not reported
OSWorld-Verified success rate74.0Best
SWE-Bench Pro resolve rate54.2
Terminal-Bench success rate · 2.1Not reported
Terminal-Bench accuracy · 2.1 · Terminus 254.0Best
Toolathlon success rateNot reported
Agentic Index index42.7Best
Agents' Last Exam score50.3Best
Artificial Analysis Coding Agent Index index score · 1.1 · Codex74.6Best
Artificial Analysis Intelligence Index index score · 4.151.2Best
BrowseComp accuracy83.3Best
CharXiv Reasoning accuracyNot reported
Coding Index index71.4Best
DeepSWE resolve rate · 1.167.2Best
FrontierMath accuracy · v278.6Best
GDM-MRCR accuracy · v2Not reported
GDPval-AA Elo · v2Not reported
GPQA Diamond accuracy92.3Best
Intelligence Index index37.5Best
MLE-Bench average position scoreNot reported
MMMU Pro accuracy78.4Best
OSWorld success rate · 2.045.6Best
OSWorld-Verified success rateNot reported
SWE-Bench Pro resolve rate62.7Best
Terminal-Bench success rate · 2.184.7Best
Terminal-Bench accuracy · 2.1 · Terminus 2Not reported
Toolathlon success rate53.4Best
Agentic Index indexNot reported
Agents' Last Exam scoreNot reported
Artificial Analysis Coding Agent Index index score · 1.1 · CodexNot reported
Artificial Analysis Intelligence Index index score · 4.1Not reported
BrowseComp accuracyNot reported
CharXiv Reasoning accuracyNot reported
Coding Index indexNot reported
DeepSWE resolve rate · 1.1Not reported
FrontierMath accuracy · v2Not reported
GDM-MRCR accuracy · v2Not reported
GDPval-AA Elo · v2Not reported
GPQA Diamond accuracyNot reported
Intelligence Index indexNot reported
MLE-Bench average position scoreNot reported
MMMU Pro accuracyNot reported
OSWorld success rate · 2.0Not reported
OSWorld-Verified success rateNot reported
SWE-Bench Pro resolve rateNot reported
Terminal-Bench success rate · 2.1Not reported
Terminal-Bench accuracy · 2.1 · Terminus 2Not reported
Toolathlon success rateNot reported

Provenance

Verification Source-linked
Confidence Medium
Last updated Sep 11, 2026
Source Models.dev
Verification Source-linked
Confidence Medium
Last updated Sep 11, 2026
Source Models.dev
Verification Source-linked
Confidence Medium
Last updated Sep 11, 2026
Source Models.dev

“Not reported” means the source catalog is silent on that field. Benchmark rows keep each published version and harness separate.