Skip to main content

Model comparison

Gemini 3 Pro vs Inkling

Data verified

Head-to-head evidence from 12 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

67.73/100
Margin
0.2pts
← winning
Thinking Machines Lab
67.54/100
1 category wins1 category wins

Public leaderboard positions: Gemini 3 Pro #19 (Supported); Inkling #20 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemini 3 Pro and Inkling share 12 comparable benchmark results. 2 of 8 categories are comparable. 15 results are unique to Gemini 3 Pro; 20 to Inkling.

Updated July 23, 2026
Shared results
12
Gemini 3 Pro only
15
Inkling only
20
Comparable categories
2 / 8

Pick Gemini 3 Pro if you want the stronger benchmark profile. Inkling only becomes the better choice if mathematics is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 12 shared benchmark results across 4 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Gemini 3 Pro has the cleaner BenchAlign overall profile here, landing at 67.73 versus 67.54. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Gemini 3 Pro's sharpest advantage is in multimodal & grounded, where it averages 81.1 against 76.5. The single biggest benchmark swing on the page is MMMU-Pro, 81% to 73.5%. Inkling does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.

Gemini 3 Pro is also the more expensive model on tokens at $2.00 input / $12.00 output per 1M tokens, versus $1.87 input / $4.68 output per 1M tokens for Inkling. That is roughly 2.6x on output cost alone. Inkling is the reasoning model in the pair, while Gemini 3 Pro is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Gemini 3 Pro gives you the larger context window at 2M, compared with 1M for Inkling.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Gemini 3 Pro and Inkling
CategoryGemini 3 ProΔInkling
MathGemini 3 Pro32.9Margin 64.2Inkling97.1
MultimodalGemini 3 Pro81.1Margin 4.6Inkling76.5
AgenticGemini 3 ProNot measuredMarginNo overlapInkling69.4
CodingGemini 3 ProNot measuredMarginNo overlapInkling68.6
ReasoningGemini 3 Pro31.1MarginNo overlapInklingNot measured
KnowledgeGemini 3 ProNot measuredMarginNo overlapInkling51.6
Inst. FollowingGemini 3 ProNot measuredMarginNo overlapInkling79.8

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Gemini 3 ProB · Inkling
  1. MMMU-Pro

    Multimodal
    Source ↗
    A 81%B 73.5%
    Winner: Gemini 3 ProΔ 7.5
    MMMU-Pro: Gemini 3 Pro scored 81%; Inkling scored 73.5%. Gemini 3 Pro wins this benchmark.
  2. CharXiv

    Multimodal
    Source ↗
    A 81.4%B 82%
    Winner: InklingΔ 0.6
    CharXiv: Gemini 3 Pro scored 81.4%; Inkling scored 82%. Inkling wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricGemini 3 ProInklingComparison
Input / output priceUSD per 1M tokensGemini 3 Pro$2 input / $12 outputInkling$1.87 input / $4.68 outputInkling has the lower combined listed price.
Generation speedtokens per secondGemini 3 Pro109 tok/sInklingNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGemini 3 Pro32.65 sInklingNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGemini 3 Pro2MInkling1MGemini 3 Pro lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGemini 3 ProInklingResult
τ²-bench resultsSource 87.1%Not comparable
Gert LabsSource 63.23%Not comparable
JobBenchSource 11.4%Not comparable
Terminal-Bench 2.0Source 63.8%Not comparable
BrowseCompSource 77.1%Not comparable
MCP AtlasSource 74.1%Not comparable
Design Arena Agentic Web DevSource 1257Not comparable
AA Agentic IndexSource 32.3%Not comparable
GDPval-AASource 36.9%Not comparable
GDPval-AASource 1239Not comparable
AA BriefcaseSource 836Not comparable
AA Tau3 BankingSource 23.7%Not comparable
Coding
BenchmarkGemini 3 ProInklingResult
Vibe Code BenchSource 14.30%Not comparable
AA-SciCodeSource 56.1%46.1%Gemini 3 Pro leads
AA LiveCodeBenchSource 91.7%Not comparable
SWE-bench VerifiedSource 77.6%Not comparable
SWE-bench ProSource 54.3%Not comparable
Terminal-Bench 2.0Source 63.8%Not comparable
AA Coding IndexSource 52.1%Not comparable
Reasoning
BenchmarkGemini 3 ProInklingResult
ARC-AGI-2Source 31.1%Not comparable
AA-LCRSource 70.7%63.3%Gemini 3 Pro leads
CritPtSource 9.1%5.4%Gemini 3 Pro leads
Knowledge
BenchmarkGemini 3 ProInklingResult
Artificial Analysis Intelligence IndexSource 39.5%40.7%Inkling leads
AA-GPQA DiamondSource 90.8%87.2%Gemini 3 Pro leads
AA-HLESource 37.2%29.7%Gemini 3 Pro leads
AA-Omniscience IndexSource 15.8%2.1%Gemini 3 Pro leads
AA-Omniscience AccuracySource 55.9%40.0%Gemini 3 Pro leads
AA-Omniscience Hallucination RateSource 90.9%63.1%Inkling leads
AA MMLU-ProSource 89.8%Not comparable
GPQASource 87.9%Not comparable
GPQA-DSource 87.9%Not comparable
HLESource 46%Not comparable
HLE w/o toolsSource 30%Not comparable
MathInkling wins
BenchmarkGemini 3 ProInklingResult
FrontierMath v2 (Tiers 1-3)Source 37.600%Not comparable
FrontierMath v2 (Tier 4)Source 18.750%Not comparable
AIME26Source 97.1%Not comparable
Multilingual
BenchmarkGemini 3 ProInklingResult
AA Global-MMLU-LiteSource 92.2%Not comparable
MultimodalGemini 3 Pro wins
BenchmarkGemini 3 ProInklingResult
MMMU-ProSource 81%73.5%Gemini 3 Pro leads
MathVisionSource 86.6%Not comparable
VideoMMMUSource 87.6%Not comparable
ScreenSpot ProSource 72.7%Not comparable
CharXivSource 81.4%82%Inkling leads
V*Source 88.0%Not comparable
AA-MMMU-ProSource 80.2%73.5%Gemini 3 Pro leads
CharXiv w/o toolsSource 78.1%Not comparable
Inst. Following
BenchmarkGemini 3 ProInklingResult
AA-IFBenchSource 70.4%Not comparable
IFBenchSource 79.8%Not comparable
Frequently Asked Questions (3)

Which is better, Gemini 3 Pro or Inkling?

Gemini 3 Pro is ahead on BenchLM's BenchAlign leaderboard, 67.73 to 67.54. The biggest single separator in this matchup is MMMU-Pro, where the scores are 81% and 73.5%.

Which is better for math, Gemini 3 Pro or Inkling?

Inkling has the edge for math in this comparison, averaging 97.1 versus 32.9. Gemini 3 Pro stays close enough that the answer can still flip depending on your workload.

Which is better for multimodal and grounded tasks, Gemini 3 Pro or Inkling?

Gemini 3 Pro has the edge for multimodal and grounded tasks in this comparison, averaging 81.1 versus 76.5. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.