Sign Up

Decision support

Gemini 4 Carbon vs GPT-6.1 Sol

Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.

ModelsHardware
Gemini 4 Carbon

Google DeepMind

Sources:models.devOpenRouter

GPT-6.1 Sol

OpenAI

Sources:models.devOpenRouter

Benchmark results

Head to head on 9 benchmarks both models report · 3 ties

  • Gemini 4 Carbon4leads
  • GPT-6.1 Sol2leads

  • Arena Text

    Arena rating · Higher is better

    • Gemini 4 Carbon
      Best1526
      +44 ahead · Arena #1CI 1516 to 1536
    • GPT-6.1 Sol
      1482
      Arena #27CI 1476 to 1488
    Runs and sources
    Gemini 4 Carbon
    • high152695% CI 1516 to 1536 · 4,282 votes
    GPT-6.1 Sol
    • max148295% CI 1476 to 1488 · 12,952 votes
    Source:Arena Text leaderboard, 2026-11-09

  • Arena WebDev

    Arena rating · Higher is better

    Tie, within 95% CI
    • Gemini 4 Carbon
      1768
      Arena #4CI 1753 to 1783
    • GPT-6.1 Sol
      1743
      Arena #6CI 1733 to 1753
    Runs and sources
    Gemini 4 Carbon
    • high176895% CI 1753 to 1783 · 2,120 votes
    GPT-6.1 Sol
    • max174395% CI 1733 to 1753 · 5,539 votes
    Source:Arena WebDev leaderboard, 2026-11-10

  • Arena Vision

    Arena rating · Higher is better

    • Gemini 4 Carbon
      Not reported
    • GPT-6.1 Sol
      1293
      Arena #12CI 1282 to 1303
    Runs and sources
    Gemini 4 Carbon

    Not reported

    GPT-6.1 Sol
    • max129395% CI 1282 to 1303 · 3,987 votes
    Source:Arena Vision leaderboard, 2026-11-09

  • Arena Search

    Arena rating · Higher is better

    • Gemini 4 Carbon
      Not reported
    • GPT-6.1 Sol
      1248
      Arena #2CI 1240 to 1256
    Runs and sources
    Gemini 4 Carbon

    Not reported

    GPT-6.1 Sol
    • max124895% CI 1240 to 1256 · 26,556 votes
    Source:Arena Search leaderboard, 2026-11-09

  • Agent Arena

    IPS score · Higher is better

    • Gemini 4 Carbon
      Best+0.170
      +0.045 ahead · Arena #3CI +0.163 to +0.177
    • GPT-6.1 Sol
      +0.125
      Arena #7CI +0.113 to +0.136
    Runs and sources
    Gemini 4 Carbon
    • high+0.17095% CI +0.163 to +0.177 · 9,558,978 observations
    GPT-6.1 Sol
    • max+0.12595% CI +0.113 to +0.136 · 3,093,307 observations
    Source:Agent Arena leaderboard, 2026-11-11

  • ARC-AGI-2

    Best published score · Higher is better

    Tie
    • Gemini 4 Carbon
      94.2%
      #2 of 85
    • GPT-6.1 Sol
      94.2%
      #2 of 85
    Runs, sources and effort chart
    Gemini 4 Carbon
    • low49.6%
    • medium94.2%
    • high92.1%
    GPT-6.1 Sol
    • low76.7%
    • medium86.7%
    • high91.7%
    • xhigh91.7%
    • max94.2%
    Source:External evaluation via Epoch AIOriginal-source terms apply

  • FrontierMath-Tier-4-v2-Private

    Best published score · Higher is better

    • Gemini 4 Carbon
      95.1%
      #4 of 72
    • GPT-6.1 Sol
      Best100.0%
      +4.9 pts ahead · #1 of 72
    Runs and sources
    Gemini 4 Carbon
    • high95.1%
    GPT-6.1 Sol
    • max100.0%
    Source:Epoch AI evaluation

  • FrontierMath-Tiers-1-3-v2-Private

    Best published score · Higher is better

    • Gemini 4 Carbon
      90.5%
      #6 of 87
    • GPT-6.1 Sol
      Best93.7%
      +3.2 pts ahead · #2 of 87
    Runs and sources
    Gemini 4 Carbon
    • high90.5%
    GPT-6.1 Sol
    • max93.7%
    Source:Epoch AI evaluation

  • GPQA diamond

    Best published score · Higher is better

    • Gemini 4 Carbon
      Best96.5%
      +1.1 pts ahead · #1 of 161
    • GPT-6.1 Sol
      95.4%
      #5 of 161
    Runs and sources
    Gemini 4 Carbon
    • high96.5%
    GPT-6.1 Sol
    • max95.4%
    Source:Epoch AI evaluation

  • OTIS Mock AIME 2024-2025

    Best published score · Higher is better

    Tie
    • Gemini 4 Carbon
      100.0%
      #1 of 158
    • GPT-6.1 Sol
      100.0%
      #1 of 158
    Runs and sources
    Gemini 4 Carbon
    • high100.0%
    GPT-6.1 Sol
    • max100.0%
    Source:Epoch AI evaluation

  • SimpleQA Verified

    Best published score · Higher is better

    • Gemini 4 Carbon
      Best77.7%
      +3.8 pts ahead · #2 of 87
    • GPT-6.1 Sol
      73.9%
      #5 of 87
    Runs and sources
    Gemini 4 Carbon
    • high77.7%
    GPT-6.1 Sol
    • max73.9%
    Source:Epoch AI evaluation

Each model's best published result is shown; "Not reported" means no matched evaluation, not a score of zero. Arena and DeepSWE ranks are the leaderboards' own; other ranks are among catalogue models with a score. Results from different harnesses or settings are not directly comparable.

Original-source terms apply to evaluations credited to their original publishers.

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.

Model specifications

Release date
October 28, 2026
September 29, 2026
Context window
1M
1.1M
Native context
—
—
Max output tokens
943,718
128,000
Knowledge cutoff
2026-03
2026-04-30
Open weights
Closed
Closed
Parameter count
—
—

API pricing · USD per 1M tokens

Input
$2.00
$2.00
Output
$10.00
$10.00
Cached input
$0.10
$0.10
Cache write
$0.1875
$2.50

Capabilities and modalities

Input modalities
audio, file, image, text, video
file, image, text
Output modalities
text
text
Tool calling
Supported
Supported
Reasoning option
Supported
Supported
Supported options
include_reasoning, max_tokens, reasoning, reasoning_effort, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p
include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, tool_choice, tools, verbosity
Capabilities
—
—

Architecture and availability

Architecture
—
—
Model families
—
—
Tokenizer
Gemini
GPT
Instruction format
—
—
License
Proprietary
—
Providers
2
3
Provider endpoints
14
18
Ollama variants
0
0
Metadata source
ai-research
ai-research

A dash means the field is not reported. Provider-specific performance and pricing may differ.

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.