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.
Bonsai 27BMiMo-V2.5Solar Open2 250B
Focus

Coding: quality vs price

Compared models are ringed; the other 111 ranked here are greyed.

Lower price is better. Pareto frontier: Granite 4.2 3B, NVIDIA Nemotron 3 Nano 30B A3B, gpt-oss-20b, Ling-3.0-flash-VL, MiMo-V2.6-Flash, Qwen3.8-Omni-Flash, GLM-5.3 Flash, DeepSeek V4.1 Flash, MiMo-V2.6-Pro, Claude Sonnet 5.5, Claude Opus 5.5. 36 models are not plotted: GLM-5.3 Flash NVFP4, Ternary Bonsai 2 27B, DeepSeek V4.1 Flash NVFP4, GLM-5.3 NVFP4, Nex-N2.5-Pro, Xing4.0-29B-A4B, Atria Dawn Preview, Ternary Bonsai 27B, Maple-Preview, Bonsai 27B, Qwen3.8 27B NVFP4, Intern-S2-397B, Solar Open2 250B, Phi-4-reasoning-plus, Motif 3, Nex-N2-Pro, Nex-N2.5-Mini, A.X-K2, K2 Horizon 375B A23B, K-EXAONE 2.0 0803, K2 Horizon MoVA 36B A4B, Intern-S2-Preview (35B-A3B), Command A+, 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.

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

GLM-5.3 Flash NVFP4, Ternary Bonsai 2 27B, DeepSeek V4.1 Flash NVFP4, GLM-5.3 NVFP4, Nex-N2.5-Pro, Xing4.0-29B-A4B, Atria Dawn Preview, Ternary Bonsai 27B, Maple-Preview, Bonsai 27B, Qwen3.8 27B NVFP4, Intern-S2-397B, Solar Open2 250B, Phi-4-reasoning-plus, Motif 3, Nex-N2-Pro, Nex-N2.5-Mini, A.X-K2, K2 Horizon 375B A23B, K-EXAONE 2.0 0803, K2 Horizon MoVA 36B A4B, Intern-S2-Preview (35B-A3B), Command A+, 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
  • Bonsai 27B
    Quality
    54.7
    Rank
    #35/114
    Price
    —
    Speed
    —

    vs Solar Open2 250B: +8.9 quality · price n/a

  • MiMo-V2.5
    Quality
    35.1
    Rank
    #65/114
    Price
    $0.18/M tok
    Speed
    40tok/s
    In$0.14Out$0.28/M tok

    vs Bonsai 27B: −19.6 quality · price n/a

  • Solar Open2 250B
    Quality
    45.8
    Rank
    #43/114
    Price
    —
    Speed
    —

    vs Bonsai 27B: −8.9 quality · price n/a

Overview

Metric
Bonsai 27B
MiMo-V2.5
Solar Open2 250B
Lab
PrismML
Xiaomi MiMo
Upstage
Released
Jul 4, 2026
Apr 22, 2026
Aug 12, 2026
Weights
Open
Open
Open
Input price
$/M tok
—
$0.14
—
Output price
$/M tok
—
$0.28
—
Blended price
$/M tok · 3:1 in:out
—
$0.175
—
Output speed
tok/s
—
40
—
Context
tokens
262K
1M
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
Bonsai 27B
MiMo-V2.5
Solar Open2 250B
Coding
54.7±10.3Best
#35/114Lab-reported
35.1±8.0
#65/114Verified
45.8±10.0
#43/114Verified
Writing & chat
56.7±9.7
#58/155Lab-reported
61.6±4.2Best
#48/155Verified
Not ranked
Vision
45.1±8.7
#57/90Lab-reported
60.0±8.2Best
#37/90Verifiedbest value
Not ranked
Hard reasoning
60.7±9.9
#52/193Lab-reported
60.6±5.9
#53/193Verifiedbest value
63.0±5.9Best
#51/193Verified
Agents
Not ranked
37.9±4.2
#72/176Verified
47.4±10.0Best
#38/176Verified

Coding benchmarks

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

Metric
Bonsai 27B
MiMo-V2.5
Solar Open2 250B
SWE-bench Verified
day 0
~#5/14~79.4%Estimated
  1. #1Claude Opus 596.0%
  2. #4MiniMax-M380.5%
  3. ~#5Bonsai 27BEstimated79.4%
  4. #5Hy378.0%
estimated from related benchmarks
~#10/14~75.0%Estimated
  1. #1Claude Opus 596.0%
  2. #9Xing4.0-29B-A4B75.0%
  3. ~#10MiMo-V2.5Estimated75.0%
  4. #10Claude Haiku 4.573.3%
estimated from related benchmarks
~#5/14~78.3%Estimated
  1. #1Claude Opus 596.0%
  2. #4MiniMax-M380.5%
  3. ~#5Solar Open2 250BEstimated78.3%
  4. #5Hy378.0%
estimated from related benchmarks
SWE-bench Pro (Public)
day 0
~#9/19~63.2%Estimated
  1. #1Claude Opus 5.589.9%
  2. #8Claude Sonnet 563.2%
  3. ~#9Bonsai 27BEstimated63.2%
  4. #9Nex-N2.5-Pro61.2%
estimated from related benchmarks
~#17/19~54.1%Estimated
  1. #1Claude Opus 5.589.9%
  2. #15Gemini 3.5 Flash-Lite54.2%
  3. ~#17MiMo-V2.5Estimated54.1%
  4. #17Muse Glimmer51.2%
estimated from related benchmarks
~#13/19~58.3%Estimated
  1. #1Claude Opus 5.589.9%
  2. #12GPT-5.558.6%
  3. ~#13Solar Open2 250BEstimated58.3%
  4. #13Hy357.9%
estimated from related benchmarks
DeepSWE v1.1
day 0
~#29/32~47.9%Estimated
  1. #1GPT-6.1 Sol75.2%
  2. #28Qwen3.8 Max (0902)51.0%
  3. ~#29Bonsai 27BEstimated47.9%
  4. #29Qwen3.8 27B42.2%
estimated from related benchmarks
~#28/32~51.6%Estimated
  1. #1GPT-6.1 Sol75.2%
  2. #27Nex-N2.5-Pro55.8%
  3. ~#28MiMo-V2.5Estimated51.6%
  4. #28Qwen3.8 Max (0902)51.0%
estimated from related benchmarks
~#28/32~54.2%Estimated
  1. #1GPT-6.1 Sol75.2%
  2. #27Nex-N2.5-Pro55.8%
  3. ~#28Solar Open2 250BEstimated54.2%
  4. #28Qwen3.8 Max (0902)51.0%
estimated from related benchmarks
Terminal-Bench 4.0
day 0
~#19/85~21.0%Estimated
  1. #1Claude Sonnet 5.563.6%
  2. #18MiMo-V2.6-Flash22.7%
  3. ~#19Bonsai 27BEstimated21.0%
  4. #19Gemini 3.8 Flash19.7%
estimated from related benchmarks
#50/840.0%Verified
  1. #1Claude Sonnet 5.563.6%
  2. #50Mercury 2.50.0%
  3. #50MiMo-V2.50.0%
  4. #50MiniCPM5-2B0.0%
artificialanalysis.ai · 2026-09-24
~#21/85~14.7%Estimated
  1. #1Claude Sonnet 5.563.6%
  2. #20Grok 4.617.2%
  3. ~#21Solar Open2 250BEstimated14.7%
  4. #21GPT-5.514.6%
estimated from related benchmarks
LiveCodeBench
third-party
#10/2476.4%Lab-reported
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #9gpt-oss-20b77.7%
  3. #10Bonsai 27B76.4%
  4. #11Maple-Preview75.1%
huggingface.co · 2026-09-30
~#12/25~66.6%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #11Maple-Preview75.1%
  3. ~#12MiMo-V2.5Estimated66.6%
  4. #12Mistral Small 464.0%
estimated from related benchmarks
~#12/25~73.1%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #11Maple-Preview75.1%
  3. ~#12Solar Open2 250BEstimated73.1%
  4. #12Mistral Small 464.0%
estimated from related benchmarks
SciCode
third-party
~#34/103~49.5%Estimated
  1. #1Claude Opus 5.566.9%
  2. #33Inkling Small49.7%
  3. ~#34Bonsai 27BEstimated49.5%
  4. #34Hy348.6%
estimated from related benchmarks
#52/10243.9%Verified
  1. #1Claude Opus 5.566.9%
  2. #51Ling-3.0-flash-VL44.2%
  3. #52MiMo-V2.543.9%
  4. #52Step 3.7 Flash43.9%
artificialanalysis.ai · 2026-09-24
#37/10248.0%BestVerified
  1. #1Claude Opus 5.566.9%
  2. #36Quasar 438B48.1%
  3. #37Solar Open2 250B48.0%
  4. #38Kimi K2.7 Code47.8%
artificialanalysis.ai · 2026-09-24
AA Coding Agent Index
third-party
~#10/15~50.3Estimated
  1. #1Claude Opus 5.566.0
  2. #9Kimi K351.9
  3. ~#10Bonsai 27BEstimated50.3
  4. #10Grok 4.647.0
estimated from related benchmarks
~last/15below measured range (<41.1)Estimated
  1. #1Claude Opus 5.566.0
  2. #14GPT-6 Luna41.1
  3. ~#15MiMo-V2.5Estimated<41.1
estimated from related benchmarks
~last/15below measured range (<41.1)Estimated
  1. #1Claude Opus 5.566.0
  2. #14GPT-6 Luna41.1
  3. ~#15Solar Open2 250BEstimated<41.1
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
Bonsai 27B
MiMo-V2.5
Solar Open2 250B
IFBench
day 0
#65/13352.4%Lab-reported
  1. #1MiniMax-M382.9%
  2. #64Jamba Reasoning 3B52.4%
  3. #65Bonsai 27B52.4%
  4. #66Qwen3.5 Omni Plus51.2%
huggingface.co · 2026-09-30
#37/13367.1%BestVerified
  1. #1MiniMax-M382.9%
  2. #36Step 3.7 Flash67.3%
  3. #37MiMo-V2.567.1%
  4. #38KAT Coder Pro V266.7%
artificialanalysis.ai · 2026-09-24
—
MMMLU
day 0
~#3/5~85.1%Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. ~#3Bonsai 27BEstimated85.1%
  4. #3Claude Haiku 4.583.0%
estimated from related benchmarks
~#3/5~86.7%Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. ~#3MiMo-V2.5Estimated86.7%
  4. #3Claude Haiku 4.583.0%
estimated from related benchmarks
—
LMArena Text, Non-English (Elo)
third-party
~#33/54~1415Estimated
  1. #1Claude Opus 5.51501
  2. #32Muse GlimmerFew votes1418
  3. ~#33Bonsai 27BEstimated1415
  4. #33MiMo-V2.51411
estimated from related benchmarks
#33/531411Verified
  1. #1Claude Opus 5.51501
  2. #32Muse GlimmerFew votes1418
  3. #33MiMo-V2.51411
  4. #34Mistral Medium 3.51406
lmarena.ai · 2026-09-13
—
LMArena Text (Elo)
third-party
~#33/54~1429Estimated
  1. #1Claude Opus 5.51509
  2. #32MiMo-V2.51434
  3. ~#33Bonsai 27BEstimated1429
  4. #33Mistral Medium 3.51426
estimated from related benchmarks
#32/531434Verified
  1. #1Claude Opus 5.51509
  2. #31Qwen3.8 27B1437
  3. #32MiMo-V2.51434
  4. #33Mistral Medium 3.51426
lmarena.ai · 2026-09-13
—
EQ-Bench Creative Writing v3 (Elo)
third-party
~#10/26~1895Estimated
  1. #1GPT-6 Astra2173
  2. #9Muse Spark 1.31906
  3. ~#10Bonsai 27BEstimated1895
  4. #10GPT-5.6 Terra1855
estimated from related benchmarks
~#13/26~1808Estimated
  1. #1GPT-6 Astra2173
  2. #12Qwen3.8 2.4T A95B1843
  3. ~#13MiMo-V2.5Estimated1808
  4. #13Muse Glimmer1798
estimated from related benchmarks
—

Vision benchmarks

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

Metric
Bonsai 27B
MiMo-V2.5
Solar Open2 250B
MMMU
day 0
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2Bonsai 27BEstimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2MiMo-V2.5Estimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
—
MMMU-Pro
day 0
#60/8460.5%Lab-reported
  1. #1Claude Opus 5.587.7%
  2. #59Nova 2.0 Omni61.9%
  3. #60Bonsai 27B60.5%
  4. #61Claude Haiku 4.558.6%
huggingface.co · 2026-09-30
#32/8475.4%BestVerified
  1. #1Claude Opus 5.587.7%
  2. #31Ternary Bonsai 2 27B75.5%
  3. #32MiMo-V2.575.4%
  4. #33Step 3.7 Flash75.3%
artificialanalysis.ai · 2026-09-24
—
CharXiv Reasoning
day 0
~#8/9~75.9%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. #7Claude Sonnet 577.0%
  3. ~#8Bonsai 27BEstimated75.9%
  4. #8Gemini 3.5 Flash-Lite74.5%
estimated from related benchmarks
~#6/9~78.5%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. #5Muse Glimmer78.8%
  3. ~#6MiMo-V2.5Estimated78.5%
  4. #6Inkling78.1%
estimated from related benchmarks
—
OmniDocBench v1.5
third-party
~#5/8~82.4%Estimated
  1. #1MiniMax-M391.6%
  2. #4Gemini 3.1 Pro85.3%
  3. ~#5Bonsai 27BEstimated82.4%
  4. #5Claude Haiku 4.579.6%
estimated from related benchmarks
~#5/8~84.4%Estimated
  1. #1MiniMax-M391.6%
  2. #4Gemini 3.1 Pro85.3%
  3. ~#5MiMo-V2.5Estimated84.4%
  4. #5Claude Haiku 4.579.6%
estimated from related benchmarks
—
GDP.pdf (AA)
third-party
~#30/43~9.3%Estimated
  1. #1GPT-6 Astra31.0%
  2. #29MiniMax-M39.8%
  3. ~#30Bonsai 27BEstimated9.3%
  4. #30Ling-3.0-flash-VL8.4%
estimated from related benchmarks
~#24/43~12.8%Estimated
  1. #1GPT-6 Astra31.0%
  2. #23Claude Sonnet 513.2%
  3. ~#24MiMo-V2.5Estimated12.8%
  4. #24DeepSeek V4.1 Flash12.8%
estimated from related benchmarks
—
Chartography
third-party
~#20/23~11.6%Estimated
  1. #1GPT-6 Astra71.0%
  2. #19DeepSeek V4.1 Flash11.6%
  3. ~#20Bonsai 27BEstimated11.6%
  4. #20Gemini 3.5 Flash-Lite10.2%
estimated from related benchmarks
~#15/23~20.3%Estimated
  1. #1GPT-6 Astra71.0%
  2. #14Grok 4.620.5%
  3. ~#15MiMo-V2.5Estimated20.3%
  4. #15Muse Glimmer17.2%
estimated from related benchmarks
—

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
Bonsai 27B
MiMo-V2.5
Solar Open2 250B
GPQA Diamond
day 0
~#70/180~79.9%Estimated
  1. #1GPT-6 Astra96.1%
  2. #69Nemotron 3 Super 120B A12B80.0%
  3. ~#70Bonsai 27BEstimated79.9%
  4. #70EXAONE 4.5 33B79.4%
estimated from related benchmarks
#51/17984.9%Verified
  1. #1GPT-6 Astra96.1%
  2. #49Ling 3.0 Flash85.5%
  3. #51MiMo-V2.584.9%
  4. #51Nanbeige4.1-3B84.9%
artificialanalysis.ai · 2026-09-24
#44/17985.7%BestVerified
  1. #1GPT-6 Astra96.1%
  2. #44Ring-2.6-1T85.7%
  3. #44Solar Open2 250B85.7%
  4. #49KAT Coder Pro V285.5%
artificialanalysis.ai · 2026-09-24
Humanity's Last Exam
day 0
~#53/182~25.2%Estimated
  1. #1Claude Opus 5.561.4%
  2. #52Qwen3.5 122B A10B25.2%
  3. ~#53Bonsai 27BEstimated25.2%
  4. #53Ling 3.0 Flash23.7%
estimated from related benchmarks
#51/18127.2%Verified
  1. #1Claude Opus 5.561.4%
  2. #50GPT-5.4 mini28.1%
  3. #51MiMo-V2.527.2%
  4. #52Qwen3.5 122B A10B25.2%
artificialanalysis.ai · 2026-09-24
#47/18128.5%BestVerified
  1. #1Claude Opus 5.561.4%
  2. #46Qwen3.5 397B A17B29.0%
  3. #47Solar Open2 250B28.5%
  4. #48Nemotron 3 Ultra28.4%
artificialanalysis.ai · 2026-09-24
AIME (latest)
day 0
#13/2987.1%Lab-reported
  1. #1GLM-5.3 NVFP499.5%
  2. #11Ternary Bonsai 27B87.5%
  3. #13Bonsai 27B87.1%
  4. #14Mistral Medium 3.586.3%
huggingface.co · 2026-09-30
~#7/30~90.6%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. #6gpt-oss-120b93.4%
  3. ~#7MiMo-V2.5Estimated90.6%
  4. #7Xing4.0-29B-A4B90.0%
estimated from related benchmarks
~#3/30~96.4%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. #2Inkling97.1%
  3. ~#3Solar Open2 250BEstimated96.4%
  4. #3Ternary Bonsai 2 27B95.8%
estimated from related benchmarks
AA Intelligence Index
third-party
~#30/78~29.0Estimated
  1. #1Claude Opus 5.557.6
  2. #29MiniMax-M329.2
  3. ~#30Bonsai 27BEstimated29.0
  4. #30Quasar 438B26.7
estimated from related benchmarks
~#32/78~26.3Estimated
  1. #1Claude Opus 5.557.6
  2. #31Apodex 1.126.4
  3. ~#32MiMo-V2.5Estimated26.3
  4. #32GPT-5.5 Instant (June 2026)26.0
estimated from related benchmarks
~#30/78~27.5Estimated
  1. #1Claude Opus 5.557.6
  2. #29MiniMax-M329.2
  3. ~#30Solar Open2 250BEstimated27.5
  4. #30Quasar 438B26.7
estimated from related benchmarks

Agents benchmarks

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

Metric
Bonsai 27B
MiMo-V2.5
Solar Open2 250B
τ²-bench (Telecom)
day 0
—
#11/11690.6%Verified
  1. #1Step 3.7 Flash98.5%
  2. #10Ring-2.6-1T92.4%
  3. #11MiMo-V2.590.6%
  4. #12Kimi K2.7 Code90.1%
artificialanalysis.ai · 2026-09-24
~#25/117~85.7%Estimated
  1. #1Step 3.7 Flash98.5%
  2. #24GPT-5.3 Codex86.0%
  3. ~#25Solar Open2 250BEstimated85.7%
  4. #25GPT-5.4 mini83.3%
estimated from related benchmarks
OSWorld-Verified
day 0
—
~#10/12~66.3%Estimated
  1. #1Kimi K384.8%
  2. #9Nex-N2.5-Mini71.2%
  3. ~#10MiMo-V2.5Estimated66.3%
  4. #10Muse Glimmer65.9%
estimated from related benchmarks
~#10/12~70.0%Estimated
  1. #1Kimi K384.8%
  2. #9Nex-N2.5-Mini71.2%
  3. ~#10Solar Open2 250BEstimated70.0%
  4. #10Muse Glimmer65.9%
estimated from related benchmarks
OSWorld 2.0
day 0
—
~last/5below measured range (<47.5%)Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #4GPT-5.547.5%
  3. ~#5MiMo-V2.5Estimated<47.5%
estimated from related benchmarks
~last/5below measured range (<47.5%)Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #4GPT-5.547.5%
  3. ~#5Solar Open2 250BEstimated<47.5%
estimated from related benchmarks
BrowseComp
day 0
—
~#15/18~63.2%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #14Inkling77.1%
  3. ~#15MiMo-V2.5Estimated63.2%
  4. #15Mistral Medium 3.548.6%
estimated from related benchmarks
~#15/18~68.7%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #14Inkling77.1%
  3. ~#15Solar Open2 250BEstimated68.7%
  4. #15Mistral Medium 3.548.6%
estimated from related benchmarks
GDPval-AA (Elo)
third-party
—
#39/86986Verified
  1. #1Claude Opus 5.51846
  2. #38GPT-5.4 mini1000
  3. #39MiMo-V2.5986
  4. #40Gemini 3.5 Flash-Lite970
artificialanalysis.ai · 2026-09-24
~#23/87~1372Estimated
  1. #1Claude Opus 5.51846
  2. #22Qwen3.8 27B1409
  3. ~#23Solar Open2 250BEstimated1372
  4. #23GPT-6 Luna1367
estimated from related benchmarks
AutomationBench-AA
third-party
—
#36/7918.4%Verified
  1. #1Claude Opus 5.569.5%
  2. #36Hy318.4%
  3. #36MiMo-V2.518.4%
  4. #38Nex-N2-Pro17.6%
artificialanalysis.ai · 2026-09-24
~#31/80~25.2%Estimated
  1. #1Claude Opus 5.569.5%
  2. #30K2 Horizon MoVA 36B A4B26.1%
  3. ~#31Solar Open2 250BEstimated25.2%
  4. #31Gemini 3.5 Flash-Lite25.0%
estimated from related benchmarks
τ-Bench Banking (AA)
third-party
—
#66/898.7%Verified
  1. #1Muse Spark 1.350.5%
  2. #65Nemotron 3.5 Lightning8.9%
  3. #66MiMo-V2.58.7%
  4. #67Granite 4.2 8B7.6%
artificialanalysis.ai · 2026-09-24
#34/8921.6%BestVerified
  1. #1Muse Spark 1.350.5%
  2. #33G9v3-39A5B22.1%
  3. #34Solar Open2 250B21.6%
  4. #35Gemini 3.1 Pro21.4%
artificialanalysis.ai · 2026-09-24