Google
Gemini 3 Pro API Benchmarks, Pricing & Provider Data
Compare Gemini 3 Pro with another model
Choose a model to open its comparison page.
LLM
Gemini 3 Pro benchmark, API pricing, and provider data cover 406 API providers, with prices starting at $0.0052/request. Gemini 3 Pro free API options are available from 7 providers. The page also shows measured API speed and first-token latency.
Google Gemini 3 Pro is a high-capability language model in the Gemini series, offering enhanced reasoning, code generation, and multimodal capabilities.
Quality
#66of 100
52.0
LMSpeed score
Speed
73char/s
10.59 s
Cost
#139of 180
$0.0052/ 1M · 8:1 in:out
$0.0008 in · $0.0044 out
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 8 / 8
- Methodology
- V3.0
#1Math55.7Provisional1/4 Measured dimensions
80% interval: 39.6–71.7
foundational mathPrior only
competition mathPrior only
proof frontier55.7
frontiermath · frontier_math_v2_tier4 / frontiermath · frontier_math_v2_tiers13
applied tool mathPrior only
#2Knowledge55.6Provisional1/4 Measured dimensions
80% interval: 41.6–69.6
broad knowledge55.6
aa_omniscience · aa_omniscience_index / benchlm_category_knowledge · benchlm_category_knowledge
professional knowledgePrior only
factualityPrior only
retrieval open bookPrior only
#3Coding55.5Estimated2/4 Measured dimensions
80% interval: 44.3–66.6
code generation65
livecodebench · livecodebench / scicode · scicode
repository engineering45.9
vibecode · vibe_code_bench
debugging testingPrior only
tooling qualityPrior only
#4Reasoning54.1RatedGlobal rank #244/4 Measured dimensions
80% interval: 47.6–60.5
abstract logic39.5
arc_agi · arc_agi2
scientific causal60.5
critpt · critpt / gpqa · gpqa / hle · hle
multistep constraints62.1
mmlu_pro · mmlu_pro
evidence verification54.2
lcr · lcr
#5Multilingual54Provisional1/4 Measured dimensions
80% interval: 36.7–71.3
cross language understanding54
global_mmlu · aa_global_mmlu_lite
multilingual generationPrior only
reasoning transferPrior only
low resource robustnessPrior only
#6Instruction following52.6Provisional1/4 Measured dimensions
80% interval: 36.6–68.6
constraint followingPrior only
structured outputPrior only
novel instruction generalization52.6
ifbench · aa_if_bench
long multiturn instructionPrior only
#7Multimodal49.9RatedGlobal rank #74/4 Measured dimensions
80% interval: 43.5–56.4
perception ocr43
v_star · v_star
document spatial49.1
charxiv · charxiv
visual reasoning51.8
mathvision · math_vision / mmmu_pro · mmmu_pro
video action55.8
screenspot · screen_spot_pro / video_mmmu · video_mmmu
#8Agents49Estimated3/4 Measured dimensions
80% interval: 39.8–58.3
planning57.3
deep_planning · gert_labs
tool use51.2
tau · tau2_bench
environment executionPrior only
recovery reliability38.5
jobbench · job_bench
Specifications
Rankings
Excels at
It's decent at
Falls behind in
Detailed scores
Updated: Aug 31, 2026Overall
undefined metric} other undefined metrics}}
Overall score52.0#66 / 100
Overall
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Pricing
undefined metric} other undefined metrics}}
Input price$2.00/M#139 / 180Output price$12.00/M#148 / 180
Pricing
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Agents
V3.0undefined metric} other undefined metrics}} · Estimated
Score4980% interval39.8–58.33/4 Measured dimensionsΤ²-bench results87.1#39 / 82Gert Labs63.2#7 / 49
Agents
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Planning & decomposition57.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
deep_planning · gert_labs · z 0.99 · q 1.00
Tool use51.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
tau · tau2_bench · z 0.05 · q 1.00
Environment & long-horizon executionPrior only
Recovery & completion reliability38.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
jobbench · job_bench · z -1.78 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Score55.580% interval44.3–66.62/4 Measured dimensionsLiveCodeBench85.7%#7 / 115SciCode49.9%#27 / 205
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Code generation65
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
livecodebench · livecodebench · z 1.62 · q 1.00
scicode · scicode · z 1.60 · q 1.00
Repository engineering45.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
vibecode · vibe_code_bench · z -0.55 · q 1.00
Debugging & testingPrior only
Tool-assisted development & qualityPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
LiveCodeBenchV3 evidence
LMSpeed rank#7
Score85.7%
Sourceartificialanalysis.ai
UpdatedAug 31, 2026
Confidence4
SciCodeV3 evidence
LMSpeed rank#27
Score49.9%
Sourceartificialanalysis.ai
UpdatedAug 31, 2026
Confidence4
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Score54.1#2480% interval47.6–60.54/4 Measured dimensionsMMLU-Pro89.5%#2 / 129GPQA88.7%#43 / 212
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Abstract logic39.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
arc_agi · arc_agi2 · z -1.58 · q 1.00
Scientific & causal reasoning60.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
critpt · critpt · z 0.51 · q 1.00
gpqa · gpqa · z 1.02 · q 1.00
hle · hle · z 0.92 · q 1.00
Multi-step constraints62.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mmlu_pro · mmlu_pro · z 1.41 · q 1.00
Evidence integration & verification54.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
lcr · lcr · z 0.20 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
MMLU-ProV3 evidence
LMSpeed rank#2
Score89.5%
Sourceartificialanalysis.ai
UpdatedAug 31, 2026
Confidence4
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score55.680% interval41.6–69.61/4 Measured dimensionsKnowledge score68.8#32 / 69Artificial Analysis Intelligence Index40.6#41 / 111
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Broad knowledge55.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aa_omniscience · aa_omniscience_index · z 0.65 · q 1.00
benchlm_category_knowledge · benchlm_category_knowledge · z 0.13 · q 1.00
Professional knowledgePrior only
FactualityPrior only
Retrieval & open-book usePrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Artificial Analysis Intelligence IndexV3 evidence
LMSpeed rank#41
Score40.6
Sourcebenchlm.ai
UpdatedAug 31, 2026
Confidence2
AA-Omniscience IndexV3 evidence
LMSpeed rank#18
Score15.3
Sourcebenchlm.ai
UpdatedAug 31, 2026
Confidence2
AA-Omniscience Hallucination Rate
LMSpeed rank#15
Score91.5
Sourcebenchlm.ai
UpdatedAug 31, 2026
Confidence2
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Score55.780% interval39.6–71.71/4 Measured dimensionsMath score56.2#32 / 62FrontierMath v2 (Tiers 1-3)37.6#14 / 47
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Foundational mathPrior only
Competition mathPrior only
Advanced proofs55.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
frontiermath · frontier_math_v2_tier4 · z 0.70 · q 1.00
frontiermath · frontier_math_v2_tiers13 · z 0.37 · q 1.00
Applied & tool-assisted mathPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
FrontierMath v2 (Tiers 1-3)V3 evidence
LMSpeed rank#14
Score37.6
Sourcebenchlm.ai
UpdatedAug 31, 2026
Confidence2
FrontierMath v2 (Tier 4)V3 evidence
LMSpeed rank#12
Score18.8
Sourcebenchlm.ai
UpdatedAug 31, 2026
Confidence2
Multilingual
V3.0undefined metric} other undefined metrics}} · Provisional
Score5480% interval36.7–71.31/4 Measured dimensionsAA Global-MMLU-Lite92.2#2 / 4
Multilingual
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Cross-language understanding54
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
global_mmlu · aa_global_mmlu_lite · z 0.00 · q 0.50
Multilingual generationPrior only
Reasoning transferPrior only
Low-resource robustnessPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Multimodal
V3.0undefined metric} other undefined metrics}} · Rated
Score49.9#780% interval43.5–56.44/4 Measured dimensionsMultimodal Grounded score67.6#15 / 44MMMU-Pro81.0#9 / 31
Multimodal
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Perception & OCR43
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
v_star · v_star · z -1.19 · q 1.00
Document & spatial understanding49.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
charxiv · charxiv · z 0.00 · q 1.00
Visual reasoning51.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mathvision · math_vision · z -0.25 · q 1.00
mmmu_pro · mmmu_pro · z 0.64 · q 1.00
Video & grounded action55.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
screenspot · screen_spot_pro · z -0.57 · q 1.00
video_mmmu · video_mmmu · z 2.19 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Score52.680% interval36.6–68.61/4 Measured dimensionsAA-IFBench70.4#34 / 84
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Constraint followingPrior only
Structured outputPrior only
Novel-instruction generalization52.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
ifbench · aa_if_bench · z 0.07 · q 1.00
Multi-turn & long instructionsPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Pricing Comparison
Compare Gemini 3 Pro API pricing across 399 providers. Prices range from $0.0052/request to $1600.00/M. KFCV50 offers the lowest rate at $0.0052/request. 7 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 99% | gemini-3-pro-preview | default | $2.80/M | $16.80/M | 106.8 t/s | 15.73 s | — | |
L1 99% | gemini-3-pro | default | $2.80/M | $16.80/M | — | — | — | |
L1 99% | gemini-3-pro-maxthinking | default | $2.80/M | $16.80/M | — | — | — | |
L1 100% | gemini-3-pro-preview | huawei-gemini | -88%$0.249/M Cache read$0.025/M | -88%$1.50/M | 83.0 t/s | 14.82 s | — | |
L1 100% | gemini-3-pro-preview-11-2025 | huawei-gemini | -88%$0.249/M | -88%$1.50/M | — | — | — | |
L1 100% | gemini-3-pro-preview-11-2025 | huawei-gemini | -94%$0.125/M | -94%$0.748/M | — | — | — | |
L1 100% | gemini-3-pro-preview | huawei-gemini | -94%$0.125/M Cache read$0.012/M | -94%$0.748/M | — | — | — | |
L1 100% | gemini-3-pro-preview | gemini-officially | $2.00/M | $12.00/M | — | — | — | |
L1 100% | gemini-3-pro-preview-low | gemini_cli | -50%$1.00/M | -50%$6.00/M | — | — | — | |
L1 100% | gemini-3-pro-preview | gemini_cli | -50%$1.00/M | -50%$6.00/M | — | — | — | |
L1 100% | gemini-3-pro-preview | default | $0.014/request | - | — | — | — | |
L1 100% | gemini-3-pro-preview-nothinking | default | -86%$0.274/M | -86%$1.64/M | — | — | — | |
L1 100% | gemini-3-pro-preview-maxthinking | default | -86%$0.274/M | -86%$1.64/M | — | — | — | |
L1 100% | gemini-3-pro-preview | default | $2.00/M Cache read$0.200/M | $12.00/M | — | — | — | |
L1 100% | gemini-3-pro-preview | default | $6.00/M | $36.00/M | — | — | — | |
兔子API Free | L1 100% | gemini-3-pro-preview-11-2025 | default | Free | Free | — | — | — |
L1 100% | gemini-3-pro | default | Free | Free | — | — | — | |
L1 100% | gemini-3-pro-preview | default | Free | Free | — | — | — | |
L1 100% | gemini-3-pro-all | default | Free | Free | — | — | — | |
L1 100% | gemini-3-pro-preview-c | default | $0.050/request | - | — | — | — |
Showing 20 model IDs of 140.
Alternatives & Similar Models
GPT-5.4
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
172 shared providers
Gemini 3 Flash
gemini-3-flash
Google Gemini 3 Flash is a next-generation fast multimodal model for responsive assistants, document understanding, and high-throughput API traffic.
172 shared providers
Gemini 3.1 Pro
gemini-3-1-pro
Google Gemini 3.1 Pro is a Gemini 3 series model with advanced multimodal reasoning, long-context support, and strong performance on coding and analytical tasks.
170 shared providers
Gemini 2.5 Pro
gemini-2-5-pro
Google Gemini 2.5 Pro is Google advanced multimodal model with a 1M-token context window, strong STEM reasoning, and native support for images, audio, and video understanding.
166 shared providers
Gemini 2.5 Flash
gemini-2-5-flash
Google Gemini 2.5 Flash is a fast multimodal model balancing speed and intelligence for chat, tool use, and large-context workloads at lower cost than Pro tiers.
163 shared providers
Claude Sonnet 4.6
claude-sonnet-4-6
Anthropic Claude Sonnet 4.6 extends the Sonnet line with improved tool use, coding reliability, and long-context performance for everyday production workloads.
162 shared providers
Frequently Asked Questions
- What benchmark data does Gemini 3 Pro include?
- LMSpeed shows Gemini 3 Pro benchmark context, API price, output speed, first-token latency, and provider data across 406 providers when those signals are available.
- What is the Gemini 3 Pro API price?
- Gemini 3 Pro has pricing from 406 providers, ranging from $0.0052/request to $1600.00/M. KFCV50 has the lowest listed price.
- What does the Gemini 3 Pro API pricing table include?
- The Gemini 3 Pro API pricing table compares 406 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest Gemini 3 Pro API pricing?
- KFCV50 currently has the lowest listed Gemini 3 Pro price at $0.0052/request across 406 providers.
- Can I compare Gemini 3 Pro API price and speed together?
- Yes. LMSpeed shows Gemini 3 Pro API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is Gemini 3 Pro API free?
- Yes, Gemini 3 Pro free API options are available through 7 providerundefined other undefined} on LMSpeed, including 兔子API, 兔子API, 兔子API, 兔子API, 兔子API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get Gemini 3 Pro free API access?
- LMSpeed currently lists 7 free API providerundefined other undefined} for Gemini 3 Pro: 兔子API, 兔子API, 兔子API, 兔子API, 兔子API. Check each provider row before using it because free tier limits can change.