Skip to content
Model Pareto

Compare models

Side by side: quality per category, price, speed, and every benchmark cell with where it came from. Pick up to four.
Gemini 4 ArgonClaude Opus 5.5Claude Sonnet 5.5
Focus

Coding: quality vs price

Compared models are ringed; the other 116 ranked here are greyed.

Lower price is better. Pareto frontier: Nex-N2.5-Mini, Nex-N2.5-Pro, MiMo-V2.6-Flash, Ternary Bonsai 2 27B, MiMo-V2.6-Pro, Gemini 4 Argon, Claude Opus 5.5. 34 models are not plotted: GLM-5.3 Flash NVFP4, DeepSeek V4.1 Flash NVFP4, GLM-5.3 NVFP4, DeepSeek-V4-Pro-0813-nvfp4-DSpark, Xing4.0-29B-A4B, Ternary Bonsai 27B, Atria Dawn Preview, Maple-Preview, Bonsai 27B, Qwen3.8 27B NVFP4, Intern-S2-397B, Phi-4-reasoning-plus, Solar Open2 250B, Laguna S 2.1, Motif 3, Nex-N2-Pro, K-EXAONE 2.0 0803, K2 Horizon 375B A23B, A.X-K2, K2 Horizon MoVA 36B A4B, Intern-S2-Preview (35B-A3B), North Mini Code, G9v3-39A5B, Falcon-H1-34B-Instruct, Qwen3.8 Flash-Next NVFP4, Devstral 2, K2 Horizon 7B, K2-Horizon-32B, Devstral Small 2, MiniCPM5-2B, Ling 3.0 Tiny, K2 Horizon 3.7B, K2 Horizon 0.9B, LFM2.5-2.6B.

34 models with no price data — shown in the strip at the left edge

GLM-5.3 Flash NVFP4, DeepSeek V4.1 Flash NVFP4, GLM-5.3 NVFP4, DeepSeek-V4-Pro-0813-nvfp4-DSpark, Xing4.0-29B-A4B, Ternary Bonsai 27B, Atria Dawn Preview, Maple-Preview, Bonsai 27B, Qwen3.8 27B NVFP4, Intern-S2-397B, Phi-4-reasoning-plus, Solar Open2 250B, Laguna S 2.1, Motif 3, Nex-N2-Pro, K-EXAONE 2.0 0803, K2 Horizon 375B A23B, A.X-K2, K2 Horizon MoVA 36B A4B, Intern-S2-Preview (35B-A3B), North Mini Code, G9v3-39A5B, Falcon-H1-34B-Instruct, Qwen3.8 Flash-Next NVFP4, Devstral 2, K2 Horizon 7B, K2-Horizon-32B, Devstral Small 2, MiniCPM5-2B, Ling 3.0 Tiny, K2 Horizon 3.7B, K2 Horizon 0.9B, LFM2.5-2.6B

  • Best-value frontier (nothing is both cheaper and better)
  • Evidencestrong → weak
  • Estimated from other categories
  • Gemini 4 Argon
    Quality
    92.4
    Rank
    #2/119
    Price
    $4.00/M tok
    Speed
    —
    In$2.00▾Out$10▾/M tok

    vs Claude Opus 5.5: −3.3 quality · 0.5× price

  • Claude Opus 5.5
    Quality
    95.7
    Rank
    #1/119
    Price
    $8.00/M tok
    Speed
    92tok/s
    In$4.00Out$20/M tok

    vs Gemini 4 Argon: +3.3 quality · 2× price

  • Claude Sonnet 5.5
    Quality
    90.6
    Rank
    #3/119
    Price
    $4.00/M tok
    Speed
    115tok/s
    In$2.00▾Out$10▾/M tok

    vs Claude Opus 5.5: −5.1 quality · 0.5× price

Overview

Metric
Gemini 4 Argon
Claude Opus 5.5
Claude Sonnet 5.5
Lab
Google DeepMind
Anthropic
Anthropic
Released
Sep 30, 2026
Sep 22, 2026
Sep 28, 2026
Weights
Proprietary
Proprietary
Proprietary
Input price
$/M tok
$2.00Best
$4.00
$2.00Best
Output price
$/M tok
$10Best
$20
$10Best
Blended price
$/M tok · 3:1 in:out
$4.00Best
$8.00
$4.00Best
Output speed
tok/s
—
92
115Best
Context
tokens
1MBest
1MBest
1MBest

Quality by category

0–100 within each category (100 = best tracked model). Rank is among all models ranked there. Click a row to focus it.

Metric
Gemini 4 Argon
Claude Opus 5.5
Claude Sonnet 5.5
Coding
92.4±4.5
#2/119Verifiedbest value
95.7±3.6Best
#1/119Mixedbest value
90.6±5.2
#3/119Mixed
Writing & chat
94.7±5.9Best
#1/156Verifiedbest value
88.3±4.3
#5/156Verified
Not ranked
Vision
Not ranked
94.0±4.8
#2/91Verifiedbest value
Not ranked
Hard reasoning
94.5±5.1
#4/200Verified
99.9±2.6Best
#1/200Verifiedbest value
95.3±4.9
#3/200Verifiedbest value
Agents
Not ranked
99.6±4.1
#1/178Verifiedbest value
Not ranked

Coding benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Gemini 4 Argon
Claude Opus 5.5
Claude Sonnet 5.5
SWE-bench Verified
day 0
~#2/14~93.3%Estimated
  1. #1Claude Opus 596.0%
  2. ~#2Gemini 4 ArgonEstimated93.3%
  3. #2Claude Sonnet 585.2%
estimated from related benchmarks
~#2/14~94.7%Estimated
  1. #1Claude Opus 596.0%
  2. ~#2Claude Opus 5.5Estimated94.7%
  3. #2Claude Sonnet 585.2%
estimated from related benchmarks
~#2/14~93.8%Estimated
  1. #1Claude Opus 596.0%
  2. ~#2Claude Sonnet 5.5Estimated93.8%
  3. #2Claude Sonnet 585.2%
estimated from related benchmarks
SWE-bench Pro (Public)
day 0
~#4/20~79.2%Estimated
  1. #1Claude Opus 5.589.9%
  2. #3Claude Fable 5.181.2%
  3. ~#4Gemini 4 ArgonEstimated79.2%
  4. #4Claude Opus 579.2%
estimated from related benchmarks
#1/1989.9%BestLab-reported
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
www-cdn.anthropic.com · 2026-09-22
#2/1981.3%Lab-reported
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #3Claude Fable 5.181.2%
anthropic.com · 2026-09-28
DeepSWE v1.1
day 0
#1/3478.8%BestVerified
  1. #1Gemini 4 Argon78.8%
  2. #2DeepSeek V4.1 Flash74.2%
artificialanalysis.ai · 2026-10-07
#10/3468.4%Verified
  1. #1Gemini 4 Argon78.8%
  2. #9GPT-6 Sol69.0%
  3. #10Claude Opus 5.568.4%
  4. #10Kimi K368.4%
artificialanalysis.ai · 2026-09-24
#7/3471.0%Lab-reported
  1. #1Gemini 4 Argon78.8%
  2. #6Muse Spark 1.371.7%
  3. #7Claude Sonnet 5.571.0%
  4. #8GPT-5.6 Terra69.6%
anthropic.com · 2026-09-28
Terminal-Bench 4.0
day 0
#4/8857.1%Verified
  1. #1Claude Sonnet 5.563.6%
  2. #3GPT-6 Astra59.1%
  3. #4Gemini 4 Argon57.1%
  4. #5GPT-6.1 Sol56.1%
artificialanalysis.ai · 2026-10-02
#2/8859.6%Verified
  1. #1Claude Sonnet 5.563.6%
  2. #2Claude Opus 5.559.6%
  3. #3GPT-6 Astra59.1%
artificialanalysis.ai · 2026-09-24
#1/8863.6%BestVerified
  1. #1Claude Sonnet 5.563.6%
  2. #2Claude Opus 5.559.6%
artificialanalysis.ai · 2026-09-28
LiveCodeBench
third-party
~#2/25~92.1%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. ~#2Gemini 4 ArgonEstimated92.1%
  3. #2Qwen3.8 Flash-Next91.9%
estimated from related benchmarks
~#2/25~91.9%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. ~#2Claude Opus 5.5Estimated91.9%
  3. #2Qwen3.8 Flash-Next91.9%
estimated from related benchmarks
~#3/25~91.7%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. ~#3Claude Sonnet 5.5Estimated91.7%
  4. #3Qwen3.8 27B90.3%
estimated from related benchmarks
SciCode
third-party
#3/10561.8%Verified
  1. #1Claude Opus 5.566.9%
  2. #2Claude Fable 5.163.1%
  3. #3Gemini 4 Argon61.8%
  4. #4Claude Sonnet 5.561.0%
artificialanalysis.ai · 2026-10-02
#1/10566.9%BestVerified
  1. #1Claude Opus 5.566.9%
  2. #2Claude Fable 5.163.1%
artificialanalysis.ai · 2026-09-24
#4/10561.0%Verified
  1. #1Claude Opus 5.566.9%
  2. #3Gemini 4 Argon61.8%
  3. #4Claude Sonnet 5.561.0%
  4. #5MiMo-V2.6-Pro60.9%
artificialanalysis.ai · 2026-09-28
AA Coding Agent Index
third-party
#2/1763.8Verified
  1. #1Claude Opus 5.566.0
  2. #2Gemini 4 Argon63.8
  3. #3GPT-6.1 Sol62.9
artificialanalysis.ai · 2026-10-07
#1/1766.0BestVerified
  1. #1Claude Opus 5.566.0
  2. #2Gemini 4 Argon63.8
artificialanalysis.ai · 2026-09-24
~#5/18~61.6Estimated
  1. #1Claude Opus 5.566.0
  2. #4Claude Fable 5.162.2
  3. ~#5Claude Sonnet 5.5Estimated61.6
  4. #5GPT-6 Astra61.6
estimated from related benchmarks
Benchmarks in other categories (4)

Writing & chat benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Gemini 4 Argon
Claude Opus 5.5
Claude Sonnet 5.5
IFBench
day 0
~#3/134~82.8%Estimated
  1. #1MiniMax-M382.9%
  2. #2Qwen3.8 2.4T A95B82.8%
  3. ~#3Gemini 4 ArgonEstimated82.8%
  4. #3Qwen3.8-Omni-Flash81.5%
estimated from related benchmarks
~#2/134~82.8%Estimated
  1. #1MiniMax-M382.9%
  2. ~#2Claude Opus 5.5Estimated82.8%
  3. #2Qwen3.8 2.4T A95B82.8%
estimated from related benchmarks
—
MMMLU
day 0
~#2/5~92.3%Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Gemini 4 ArgonEstimated92.3%
  3. #2Gemma 4 31B88.4%
estimated from related benchmarks
~#2/5~92.3%Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Claude Opus 5.5Estimated92.3%
  3. #2Gemma 4 31B88.4%
estimated from related benchmarks
—
LMArena Text, Non-English (Elo)
third-party
#1/561512BestVerifiedFew votes
  1. #1Gemini 4 ArgonFew votes1512
  2. #2Claude Fable 5.1Few votes1496
lmarena.ai · 2026-10-02
#3/561494Verified
  1. #1Gemini 4 ArgonFew votes1512
  2. #2Claude Fable 5.1Few votes1496
  3. #3Claude Opus 5.51494
  4. #4Muse Spark 1.3Few votes1487
lmarena.ai · 2026-10-02
—
LMArena Text (Elo)
third-party
#1/561525BestVerified
  1. #1Gemini 4 Argon1525
  2. #2Claude Opus 5.51504
lmarena.ai · 2026-10-02
#2/561504Verified
  1. #1Gemini 4 Argon1525
  2. #2Claude Opus 5.51504
  3. #3Claude Fable 5.11501
lmarena.ai · 2026-10-02
—
EQ-Bench Creative Writing v3 (Elo)
third-party
~#7/26~2064Estimated
  1. #1GPT-6 Astra2173
  2. #6GLM-5.32075
  3. ~#7Gemini 4 ArgonEstimated2064
  4. #7Claude Opus 5.52050
estimated from related benchmarks
#7/252050Verified
  1. #1GPT-6 Astra2173
  2. #6GLM-5.32075
  3. #7Claude Opus 5.52050
  4. #8Grok 4.72007
eqbench.com · 2026-09-24
—

Vision benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Gemini 4 Argon
Claude Opus 5.5
Claude Sonnet 5.5
MMMU
day 0
—
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2Claude Opus 5.5Estimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
—
MMMU-Pro
day 0
—
#1/8587.7%Verified
  1. #1Claude Opus 5.587.7%
  2. #2GPT-6 Astra86.9%
artificialanalysis.ai · 2026-09-24
—
CharXiv Reasoning
day 0
—
~#2/9~86.1%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. ~#2Claude Opus 5.5Estimated86.1%
  3. #2Kimi K384.8%
estimated from related benchmarks
—
OmniDocBench v1.5
third-party
—
~#2/8~91.4%Estimated
  1. #1MiniMax-M391.6%
  2. ~#2Claude Opus 5.5Estimated91.4%
  3. #2Kimi K391.1%
estimated from related benchmarks
—
GDP.pdf (AA)
third-party
—
#4/4326.2%Verified
  1. #1GPT-6.1 Sol32.0%
  2. #4Claude Fable 5.126.2%
  3. #4Claude Opus 5.526.2%
  4. #6GPT-6 Sol24.8%
artificialanalysis.ai · 2026-09-24
—
Chartography
third-party
—
#2/2366.3%Verified
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #3GPT-6 Sol53.6%
surgehq.ai · 2026-09-24
—

Hard reasoning benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Gemini 4 Argon
Claude Opus 5.5
Claude Sonnet 5.5
GPQA Diamond
day 0
~#2/184~96.1%Estimated
  1. #1GPT-6 Astra96.1%
  2. ~#2Gemini 4 ArgonEstimated96.1%
  3. #2Gemini 3.8 Flash95.3%
estimated from related benchmarks
~#2/184~96.1%Estimated
  1. #1GPT-6 Astra96.1%
  2. ~#2Claude Opus 5.5Estimated96.1%
  3. #2Gemini 3.8 Flash95.3%
estimated from related benchmarks
~#2/184~96.1%Estimated
  1. #1GPT-6 Astra96.1%
  2. ~#2Claude Sonnet 5.5Estimated96.1%
  3. #2Gemini 3.8 Flash95.3%
estimated from related benchmarks
Humanity's Last Exam
day 0
#3/18457.1%Verified
  1. #1Claude Opus 5.561.4%
  2. #2Claude Fable 5.159.1%
  3. #3Gemini 4 Argon57.1%
  4. #4Claude Sonnet 5.555.0%
artificialanalysis.ai · 2026-10-02
#1/18461.4%BestVerified
  1. #1Claude Opus 5.561.4%
  2. #2Claude Fable 5.159.1%
artificialanalysis.ai · 2026-09-24
#4/18455.0%Verified
  1. #1Claude Opus 5.561.4%
  2. #3Gemini 4 Argon57.1%
  3. #4Claude Sonnet 5.555.0%
  4. #5Claude Opus 554.9%
artificialanalysis.ai · 2026-09-28
AIME (latest)
day 0
~#2/32~99.1%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2Gemini 4 ArgonEstimated99.1%
  3. #2Inkling97.1%
estimated from related benchmarks
~#2/32~99.2%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2Claude Opus 5.5Estimated99.2%
  3. #2Inkling97.1%
estimated from related benchmarks
~#2/32~99.0%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2Claude Sonnet 5.5Estimated99.0%
  3. #2Inkling97.1%
estimated from related benchmarks
AA Intelligence Index
third-party
#5/8552.6Verified
  1. #1Claude Opus 5.557.6
  2. #4GPT-6 Astra52.7
  3. #5Gemini 4 Argon52.6
  4. #6GPT-6.1 Sol51.8
artificialanalysis.ai · 2026-10-02
#1/8557.6BestVerified
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556.0
artificialanalysis.ai · 2026-09-24
#2/8556.0Verified
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556.0
  3. #3Claude Fable 5.153.4
artificialanalysis.ai · 2026-09-28

Agents benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Gemini 4 Argon
Claude Opus 5.5
Claude Sonnet 5.5
τ²-bench (Telecom)
day 0
—
~#2/118~98.3%Estimated
  1. #1Step 3.7 Flash98.5%
  2. ~#2Claude Opus 5.5Estimated98.3%
  3. #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
estimated from related benchmarks
—
OSWorld-Verified
day 0
—
~#2/12~84.6%Estimated
  1. #1Kimi K384.8%
  2. ~#2Claude Opus 5.5Estimated84.6%
  3. #2Qwen3.8 27B84.3%
estimated from related benchmarks
—
OSWorld 2.0
day 0
—
~#2/5~58.6%Estimated
  1. #1GLM-5.3 Flash59.1%
  2. ~#2Claude Opus 5.5Estimated58.6%
  3. #2Kimi K358.3%
estimated from related benchmarks
—
BrowseComp
day 0
—
~#2/18~92.3%Estimated
  1. #1Atria Dawn Preview92.5%
  2. ~#2Claude Opus 5.5Estimated92.3%
  3. #2GPT-6 Astra91.5%
estimated from related benchmarks
—
GDPval-AA (Elo)
third-party
—
#1/871866Verified
  1. #1Claude Opus 5.51866
  2. #2Claude Fable 5.11758
artificialanalysis.ai · 2026-10-07
—
AutomationBench-AA
third-party
—
#1/8169.5%Verified
  1. #1Claude Opus 5.569.5%
  2. #2DeepSeek V4.1 Flash68.9%
artificialanalysis.ai · 2026-09-24
—
τ-Bench Banking (AA)
third-party
—
~#3/90~50.1%Estimated
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. ~#3Claude Opus 5.5Estimated50.1%
  4. #3Qwen3.8 2.4T A95B49.1%
estimated from related benchmarks
—
Not comparable across labs (1)
OSWorld 2.0 (Sept 2026 release)
day 0
—
#1/381.8%Lab-reported
  1. #1Claude Opus 5.581.8%
  2. #2Claude Fable 5.180.7%
anthropic.com · 2026-09-22
—