THE SCOREBOARD FOR WHAT'S NEXTAI + QUANTUM, SCORED. COMPARED. EXPLAINED.
AIQUANTUMSCORE.

Google / Gemini

Gemini 3.1 Pro Preview

Version gemini-3-1-pro-preview · Released 2026-02-19 · Preview

Compare this model ↗
46QUANTUM SCORE

Explore Google history →

THE PRACTICAL READ

Should you shortlist Gemini 3.1 Pro Preview?

Evidence checked 2026-10-01. This interpretation uses the cited records below; it is not a hands-on review.

What the evidence supports

The strongest relative category results in our current evidence are math and reasoning. Scores describe this comparison pool, not a percentage of real-world tasks solved.

10 current independent benchmark observations. Several tasks from one suite do not count as separate independent sources.

What remains uncertain

Category coverage does not establish reliability on your own workload. Writing quality, factual accuracy, privacy and production reliability require separate evaluation.

An overall score summarizes covered categories; a high overall score may not match your priorities. Check the effort level and tool configuration before comparing results.

Inspect coverage →

Cost and response time

At 10M input + 2M output tokens, the base API estimate is $44.00/month. This excludes tools, caching, batch rates, subscriptions and taxes.

Output tokens per second measures generation after it starts. Reasoning time can make a fast-generating model take longer to finish. Use the measured speed and effort records below.

Estimate your actual usage →

Alternatives worth comparing

Gemini 3.7 Flash

10 shared independent observations with matching test methods.

Same illustrative usage: $15.00/month ($29.00 less). Lower price does not establish equivalent task performance.

Compare tradeoffs →

Grok 4.5

10 shared independent observations with matching test methods.

Same illustrative usage: $32.00/month ($12.00 less). Lower price does not establish equivalent task performance.

Compare tradeoffs →

Gemini 3.5 Flash

10 shared independent observations with matching test methods.

Same illustrative usage: $33.00/month ($11.00 less). Lower price does not establish equivalent task performance.

Compare tradeoffs →

Follow changes to this model ↗ Choose an AI for coding → · Research guide → · Automation guide →

Coding19
Reasoning81
Math82
REVAL™
ⓘREVAL™ Research Evaluation Index — our proprietary 0–100 benchmark measuring real-world AI research performance. Methodology →
Not tested
Agents0
Multimodal71
SpeedNot measured
Value35

PROPRIETARY / RESEARCH EVALUATION INDEX

REVAL™ Not tested

Methodology →

This exact model version has not completed a reviewed REVAL evaluation. No score is assigned from reputation or external benchmarks.

01 / EVIDENCE

Benchmark breakdown

BenchmarkVersionMethodConfigurationResultTest dateVerifiedSource typeSource
LiveBench code_completion2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · gemini-3.1-pro-preview-high78.261 %not published2026-09-30benchmark maintainerView source ↗
LiveBench code_generation2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · gemini-3.1-pro-preview-high74.648 %not published2026-09-30benchmark maintainerView source ↗
LiveBench javascript2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · gemini-3.1-pro-preview-high59.091 %not published2026-09-30benchmark maintainerView source ↗
LiveBench AMPS_Hard2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · gemini-3.1-pro-preview-high98 %not published2026-09-30benchmark maintainerView source ↗
LiveBench olympiad2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · gemini-3.1-pro-preview-high92.102 %not published2026-09-30benchmark maintainerView source ↗
LiveBench theory_of_mind2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · gemini-3.1-pro-preview-high80.769 %not published2026-09-30benchmark maintainerView source ↗
LiveBench zebra_puzzle2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · gemini-3.1-pro-preview-high85.25 %not published2026-09-30benchmark maintainerView source ↗
MMMU-Pro Mercor public leaderboardMMMU-Pro Mercor public setMercor independent evaluation1730 public tasks; Pass@1; model effort recorded separately · High84.3 %not published2026-09-30independent labView source ↗
DeepSWE v1.1 maintainer pass@11.1mini-swe-agent; 113-task set; best published reasoning configuration per model; provider/verifier/network errors excluded as documentedmini-swe-agent; 113 tasks; best published reasoning configuration · high11.725664 %not published2026-10-01benchmark maintainerView source ↗
Terminal-Bench 4.0 Vals mini-SWE-agent avg@3 fallbacks failed4.0Vals mini-SWE-agent avg@3; Anthropic fallbacks treated as failures— · high2.525 %not published2026-10-01independent labView source ↗

02 / COST

Price & speed

Input / 1M tokens $2.00

Output / 1M tokens $12.00

Cached input / 1M —

Batch input / 1M —

Batch output / 1M —

Speed No comparable observation yet

Price verified 2026-09-29

Price scope Prompts up to 200k tokens; higher long-context rate

Price source Official pricing ↗

02A / PERFORMANCE

Measured speed

No sourced speed measurement at a stated effort level yet.

03 / PROFILE

Capabilities

visiontool use

04 / CONTEXT

Evidence coverage & limits

Published tests describe specific environments and effort settings. They do not establish performance on every task. Read the practical interpretation above →

Coverage: 85% · Moderate confidence · 10 observations · 4 source domains (4 independent).

05 / HISTORY

Version & price history

Version gemini-3-1-pro-preview · released 2026-02-19.

2026-09-29: $2.00 input / $12.00 output per 1M tokens · Price source ↗

06 / SOURCES

Source records

DATED EVIDENCE

History

Standard API price history

2026-09-292026-09-29
  • 2026-09-29: 4.5 USD / 1M · 75% input / 25% output USD per 1M · source ↗

One observation; no trend can be inferred.

LiveBench code_completion / 2026-06-25 / %

2026-09-302026-09-30
  • 2026-09-30: 78.261 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench code_generation / 2026-06-25 / %

2026-09-302026-09-30
  • 2026-09-30: 74.648 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench javascript / 2026-06-25 / %

2026-09-302026-09-30
  • 2026-09-30: 59.091 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench AMPS_Hard / 2026-06-25 / %

2026-09-302026-09-30
  • 2026-09-30: 98 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench olympiad / 2026-06-25 / %

2026-09-302026-09-30
  • 2026-09-30: 92.102 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench theory_of_mind / 2026-06-25 / %

2026-09-302026-09-30
  • 2026-09-30: 80.769 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench zebra_puzzle / 2026-06-25 / %

2026-09-302026-09-30
  • 2026-09-30: 85.25 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

MMMU-Pro Mercor public leaderboard / MMMU-Pro Mercor public set / %

2026-09-302026-09-30
  • 2026-09-30: 84.3 result · Mercor independent evaluation · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

DeepSWE v1.1 maintainer pass@1 / 1.1 / %

2026-10-012026-10-01
  • 2026-10-01: 11.726 result · mini-swe-agent; 113-task set; best published reasoning configuration per model; provider/verifier/network errors excluded as documented · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

Terminal-Bench 4.0 Vals mini-SWE-agent avg@3 fallbacks failed / 4.0 / %

2026-10-012026-10-01
  • 2026-10-01: 2.525 result · Vals mini-SWE-agent avg@3; Anthropic fallbacks treated as failures · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

coding category score history

2026-10-012026-11-07
  • 2026-10-01: 37 score · Scoring 3.0.0
  • 2026-10-02: 19 score · Scoring 3.0.0
  • 2026-10-03: 19 score · Scoring 3.0.0
  • 2026-10-04: 19 score · Scoring 3.0.0
  • 2026-10-05: 19 score · Scoring 3.0.0
  • 2026-10-06: 19 score · Scoring 3.0.0
  • 2026-10-07: 19 score · Scoring 3.0.0
  • 2026-10-08: 19 score · Scoring 3.0.0
  • 2026-10-09: 19 score · Scoring 3.0.0
  • 2026-10-10: 19 score · Scoring 3.0.0
  • 2026-10-11: 19 score · Scoring 3.0.0
  • 2026-10-12: 19 score · Scoring 3.0.0
  • 2026-10-13: 19 score · Scoring 3.0.0
  • 2026-10-14: 19 score · Scoring 3.0.0
  • 2026-10-15: 19 score · Scoring 3.0.0
  • 2026-10-16: 19 score · Scoring 3.0.0
  • 2026-10-17: 19 score · Scoring 3.0.0
  • 2026-10-18: 19 score · Scoring 3.0.0
  • 2026-10-19: 19 score · Scoring 3.0.0
  • 2026-10-20: 19 score · Scoring 3.0.0
  • 2026-10-21: 19 score · Scoring 3.0.0
  • 2026-10-22: 19 score · Scoring 3.0.0
  • 2026-10-23: 19 score · Scoring 3.0.0
  • 2026-10-24: 19 score · Scoring 3.0.0
  • 2026-10-25: 19 score · Scoring 3.0.0
  • 2026-10-26: 19 score · Scoring 3.0.0
  • 2026-10-27: 19 score · Scoring 3.0.0
  • 2026-10-28: 19 score · Scoring 3.0.0
  • 2026-10-29: 19 score · Scoring 3.0.0
  • 2026-10-30: 19 score · Scoring 3.0.0
  • 2026-10-31: 19 score · Scoring 3.0.0
  • 2026-11-01: 19 score · Scoring 3.0.0
  • 2026-11-02: 19 score · Scoring 3.0.0
  • 2026-11-03: 19 score · Scoring 3.0.0
  • 2026-11-04: 19 score · Scoring 3.0.0
  • 2026-11-05: 19 score · Scoring 3.0.0
  • 2026-11-06: 19 score · Scoring 3.0.0
  • 2026-11-07: 19 score · Scoring 3.0.0

reasoning category score history

2026-10-012026-11-07
  • 2026-10-01: 81 score · Scoring 3.0.0
  • 2026-10-02: 81 score · Scoring 3.0.0
  • 2026-10-03: 81 score · Scoring 3.0.0
  • 2026-10-04: 81 score · Scoring 3.0.0
  • 2026-10-05: 81 score · Scoring 3.0.0
  • 2026-10-06: 81 score · Scoring 3.0.0
  • 2026-10-07: 81 score · Scoring 3.0.0
  • 2026-10-08: 81 score · Scoring 3.0.0
  • 2026-10-09: 81 score · Scoring 3.0.0
  • 2026-10-10: 81 score · Scoring 3.0.0
  • 2026-10-11: 81 score · Scoring 3.0.0
  • 2026-10-12: 81 score · Scoring 3.0.0
  • 2026-10-13: 81 score · Scoring 3.0.0
  • 2026-10-14: 81 score · Scoring 3.0.0
  • 2026-10-15: 81 score · Scoring 3.0.0
  • 2026-10-16: 81 score · Scoring 3.0.0
  • 2026-10-17: 81 score · Scoring 3.0.0
  • 2026-10-18: 81 score · Scoring 3.0.0
  • 2026-10-19: 81 score · Scoring 3.0.0
  • 2026-10-20: 81 score · Scoring 3.0.0
  • 2026-10-21: 81 score · Scoring 3.0.0
  • 2026-10-22: 81 score · Scoring 3.0.0
  • 2026-10-23: 81 score · Scoring 3.0.0
  • 2026-10-24: 81 score · Scoring 3.0.0
  • 2026-10-25: 81 score · Scoring 3.0.0
  • 2026-10-26: 81 score · Scoring 3.0.0
  • 2026-10-27: 81 score · Scoring 3.0.0
  • 2026-10-28: 81 score · Scoring 3.0.0
  • 2026-10-29: 81 score · Scoring 3.0.0
  • 2026-10-30: 81 score · Scoring 3.0.0
  • 2026-10-31: 81 score · Scoring 3.0.0
  • 2026-11-01: 81 score · Scoring 3.0.0
  • 2026-11-02: 81 score · Scoring 3.0.0
  • 2026-11-03: 81 score · Scoring 3.0.0
  • 2026-11-04: 81 score · Scoring 3.0.0
  • 2026-11-05: 81 score · Scoring 3.0.0
  • 2026-11-06: 81 score · Scoring 3.0.0
  • 2026-11-07: 81 score · Scoring 3.0.0

math category score history

2026-10-012026-11-07
  • 2026-10-01: 82 score · Scoring 3.0.0
  • 2026-10-02: 82 score · Scoring 3.0.0
  • 2026-10-03: 82 score · Scoring 3.0.0
  • 2026-10-04: 82 score · Scoring 3.0.0
  • 2026-10-05: 82 score · Scoring 3.0.0
  • 2026-10-06: 82 score · Scoring 3.0.0
  • 2026-10-07: 82 score · Scoring 3.0.0
  • 2026-10-08: 82 score · Scoring 3.0.0
  • 2026-10-09: 82 score · Scoring 3.0.0
  • 2026-10-10: 82 score · Scoring 3.0.0
  • 2026-10-11: 82 score · Scoring 3.0.0
  • 2026-10-12: 82 score · Scoring 3.0.0
  • 2026-10-13: 82 score · Scoring 3.0.0
  • 2026-10-14: 82 score · Scoring 3.0.0
  • 2026-10-15: 82 score · Scoring 3.0.0
  • 2026-10-16: 82 score · Scoring 3.0.0
  • 2026-10-17: 82 score · Scoring 3.0.0
  • 2026-10-18: 82 score · Scoring 3.0.0
  • 2026-10-19: 82 score · Scoring 3.0.0
  • 2026-10-20: 82 score · Scoring 3.0.0
  • 2026-10-21: 82 score · Scoring 3.0.0
  • 2026-10-22: 82 score · Scoring 3.0.0
  • 2026-10-23: 82 score · Scoring 3.0.0
  • 2026-10-24: 82 score · Scoring 3.0.0
  • 2026-10-25: 82 score · Scoring 3.0.0
  • 2026-10-26: 82 score · Scoring 3.0.0
  • 2026-10-27: 82 score · Scoring 3.0.0
  • 2026-10-28: 82 score · Scoring 3.0.0
  • 2026-10-29: 82 score · Scoring 3.0.0
  • 2026-10-30: 82 score · Scoring 3.0.0
  • 2026-10-31: 82 score · Scoring 3.0.0
  • 2026-11-01: 82 score · Scoring 3.0.0
  • 2026-11-02: 82 score · Scoring 3.0.0
  • 2026-11-03: 82 score · Scoring 3.0.0
  • 2026-11-04: 82 score · Scoring 3.0.0
  • 2026-11-05: 82 score · Scoring 3.0.0
  • 2026-11-06: 82 score · Scoring 3.0.0
  • 2026-11-07: 82 score · Scoring 3.0.0

agents category score history

2026-10-012026-11-07
  • 2026-10-01: 0 score · Scoring 3.0.0
  • 2026-10-02: 0 score · Scoring 3.0.0
  • 2026-10-03: 0 score · Scoring 3.0.0
  • 2026-10-04: 0 score · Scoring 3.0.0
  • 2026-10-05: 0 score · Scoring 3.0.0
  • 2026-10-06: 0 score · Scoring 3.0.0
  • 2026-10-07: 0 score · Scoring 3.0.0
  • 2026-10-08: 0 score · Scoring 3.0.0
  • 2026-10-09: 0 score · Scoring 3.0.0
  • 2026-10-10: 0 score · Scoring 3.0.0
  • 2026-10-11: 0 score · Scoring 3.0.0
  • 2026-10-12: 0 score · Scoring 3.0.0
  • 2026-10-13: 0 score · Scoring 3.0.0
  • 2026-10-14: 0 score · Scoring 3.0.0
  • 2026-10-15: 0 score · Scoring 3.0.0
  • 2026-10-16: 0 score · Scoring 3.0.0
  • 2026-10-17: 0 score · Scoring 3.0.0
  • 2026-10-18: 0 score · Scoring 3.0.0
  • 2026-10-19: 0 score · Scoring 3.0.0
  • 2026-10-20: 0 score · Scoring 3.0.0
  • 2026-10-21: 0 score · Scoring 3.0.0
  • 2026-10-22: 0 score · Scoring 3.0.0
  • 2026-10-23: 0 score · Scoring 3.0.0
  • 2026-10-24: 0 score · Scoring 3.0.0
  • 2026-10-25: 0 score · Scoring 3.0.0
  • 2026-10-26: 0 score · Scoring 3.0.0
  • 2026-10-27: 0 score · Scoring 3.0.0
  • 2026-10-28: 0 score · Scoring 3.0.0
  • 2026-10-29: 0 score · Scoring 3.0.0
  • 2026-10-30: 0 score · Scoring 3.0.0
  • 2026-10-31: 0 score · Scoring 3.0.0
  • 2026-11-01: 0 score · Scoring 3.0.0
  • 2026-11-02: 0 score · Scoring 3.0.0
  • 2026-11-03: 0 score · Scoring 3.0.0
  • 2026-11-04: 0 score · Scoring 3.0.0
  • 2026-11-05: 0 score · Scoring 3.0.0
  • 2026-11-06: 0 score · Scoring 3.0.0
  • 2026-11-07: 0 score · Scoring 3.0.0

multimodal category score history

2026-10-012026-11-07
  • 2026-10-01: 71 score · Scoring 3.0.0
  • 2026-10-02: 71 score · Scoring 3.0.0
  • 2026-10-03: 71 score · Scoring 3.0.0
  • 2026-10-04: 71 score · Scoring 3.0.0
  • 2026-10-05: 71 score · Scoring 3.0.0
  • 2026-10-06: 71 score · Scoring 3.0.0
  • 2026-10-07: 71 score · Scoring 3.0.0
  • 2026-10-08: 71 score · Scoring 3.0.0
  • 2026-10-09: 71 score · Scoring 3.0.0
  • 2026-10-10: 71 score · Scoring 3.0.0
  • 2026-10-11: 71 score · Scoring 3.0.0
  • 2026-10-12: 71 score · Scoring 3.0.0
  • 2026-10-13: 71 score · Scoring 3.0.0
  • 2026-10-14: 71 score · Scoring 3.0.0
  • 2026-10-15: 71 score · Scoring 3.0.0
  • 2026-10-16: 71 score · Scoring 3.0.0
  • 2026-10-17: 71 score · Scoring 3.0.0
  • 2026-10-18: 71 score · Scoring 3.0.0
  • 2026-10-19: 71 score · Scoring 3.0.0
  • 2026-10-20: 71 score · Scoring 3.0.0
  • 2026-10-21: 71 score · Scoring 3.0.0
  • 2026-10-22: 71 score · Scoring 3.0.0
  • 2026-10-23: 71 score · Scoring 3.0.0
  • 2026-10-24: 71 score · Scoring 3.0.0
  • 2026-10-25: 71 score · Scoring 3.0.0
  • 2026-10-26: 71 score · Scoring 3.0.0
  • 2026-10-27: 71 score · Scoring 3.0.0
  • 2026-10-28: 71 score · Scoring 3.0.0
  • 2026-10-29: 71 score · Scoring 3.0.0
  • 2026-10-30: 71 score · Scoring 3.0.0
  • 2026-10-31: 71 score · Scoring 3.0.0
  • 2026-11-01: 71 score · Scoring 3.0.0
  • 2026-11-02: 71 score · Scoring 3.0.0
  • 2026-11-03: 71 score · Scoring 3.0.0
  • 2026-11-04: 71 score · Scoring 3.0.0
  • 2026-11-05: 71 score · Scoring 3.0.0
  • 2026-11-06: 71 score · Scoring 3.0.0
  • 2026-11-07: 71 score · Scoring 3.0.0

07 / EXPLORE

Similar models