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.
Ring-2.6-1TLing-3.0-flash-FinQuasar 438B
Focus

Coding: quality vs price

Compared models are ringed; the other 100 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, GLM-5.3 Flash, DeepSeek V4.1 Flash, MiMo-V2.6-Pro, Claude Sonnet 5.5, Claude Opus 5.5. 26 models are not plotted: Xing4.0-29B-A4B, Nex-N2.5-Pro, Atria Dawn Preview, 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, Devstral 2, K2 Horizon 7B, Devstral Small 2, MiniCPM5-2B, Ling 3.0 Tiny, K2 Horizon 3.7B, K2 Horizon 0.9B, LFM2.5-2.6B.

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

Xing4.0-29B-A4B, Nex-N2.5-Pro, Atria Dawn Preview, 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, Devstral 2, K2 Horizon 7B, 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
  • Ring-2.6-1T
    Quality
    35.7
    Rank
    #59/103
    Price
    $0.85/M tok
    Speed
    119tok/s
    In$0.30Out$2.50/M tok

    vs Quasar 438B: −3.4 quality · 0.94× price

  • Ling-3.0-flash-Fin
    Quality
    33.4
    Rank
    #67/103
    Price
    $0.11/M tok
    Speed
    159tok/s
    In$0.075▾Out$0.22▾/M tok

    vs Quasar 438B: −5.8 quality · 0.12× price

  • Quasar 438B
    Quality
    39.1
    Rank
    #47/103
    Price
    $0.90/M tok
    Speed
    152tok/s
    In$0.60Out$1.80/M tok

    vs Ring-2.6-1T: +3.4 quality · 1.1× price

Overview

Metric
Ring-2.6-1T
Ling-3.0-flash-Fin
Quasar 438B
Lab
inclusionAI (Ant Group)
inclusionAI (Ant Group)
Multiverse Computing
Released
May 8, 2026
Aug 27, 2026
Aug 10, 2026
Weights
Open
Open
Proprietary
Input price
$/M tok
$0.30
$0.075Best
$0.60
Output price
$/M tok
$2.50
$0.22Best
$1.80
Blended price
$/M tok · 3:1 in:out
$0.85
$0.111Best
$0.90
Output speed
tok/s
119
159Best
152
Context
tokens
262K
262K
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
Ring-2.6-1T
Ling-3.0-flash-Fin
Quasar 438B
Coding
35.7±8.0
#59/103Verified
33.4±8.0
#67/103Verified
39.2±8.0Best
#47/103Verified
Writing & chat
38.1±9.5
#78/146Verified
Not ranked
Not ranked
Hard reasoning
51.1±3.7
#67/182Verified
51.3±5.1Best
#66/182Verified
50.2±3.7
#68/182Verified
Agents
36.0±4.2
#73/173Verified
Not ranked
43.9±5.8Best
#49/173Verified

Coding benchmarks

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

Metric
Ring-2.6-1T
Ling-3.0-flash-Fin
Quasar 438B
SWE-bench Verified
day 0
~#10/14~74.4%Estimated
  1. #1Claude Opus 596.0%
  2. #9Xing4.0-29B-A4B75.0%
  3. ~#10Ring-2.6-1TEstimated74.4%
  4. #10Claude Haiku 4.573.3%
estimated from related benchmarks
~#11/14~73.3%Estimated
  1. #1Claude Opus 596.0%
  2. #10Claude Haiku 4.573.3%
  3. ~#11Ling-3.0-flash-FinEstimated73.3%
  4. #11Nemotron 3 Ultra70.7%
estimated from related benchmarks
~#9/14~76.0%Estimated
  1. #1Claude Opus 596.0%
  2. #8Muse Glimmer76.0%
  3. ~#9Quasar 438BEstimated76.0%
  4. #9Xing4.0-29B-A4B75.0%
estimated from related benchmarks
SWE-bench Pro (Public)
day 0
~#17/19~53.4%Estimated
  1. #1Claude Opus 5.589.9%
  2. #15Gemini 3.5 Flash-Lite54.2%
  3. ~#17Ring-2.6-1TEstimated53.4%
  4. #17Muse Glimmer51.2%
estimated from related benchmarks
~#17/19~52.3%Estimated
  1. #1Claude Opus 5.589.9%
  2. #15Gemini 3.5 Flash-Lite54.2%
  3. ~#17Ling-3.0-flash-FinEstimated52.3%
  4. #17Muse Glimmer51.2%
estimated from related benchmarks
~#14/19~55.0%Estimated
  1. #1Claude Opus 5.589.9%
  2. #13Hy357.9%
  3. ~#14Quasar 438BEstimated55.0%
  4. #14Inkling54.3%
estimated from related benchmarks
DeepSWE v1.1
day 0
~#27/31~51.3%Estimated
  1. #1DeepSeek V4.1 Flash74.2%
  2. #26Nex-N2.5-Pro55.8%
  3. ~#27Ring-2.6-1TEstimated51.3%
  4. #27Qwen3.8 Max (0902)51.0%
estimated from related benchmarks
~#28/31~49.3%Estimated
  1. #1DeepSeek V4.1 Flash74.2%
  2. #27Qwen3.8 Max (0902)51.0%
  3. ~#28Ling-3.0-flash-FinEstimated49.3%
  4. #28Qwen3.8 27B42.2%
estimated from related benchmarks
~#27/31~53.6%Estimated
  1. #1DeepSeek V4.1 Flash74.2%
  2. #26Nex-N2.5-Pro55.8%
  3. ~#27Quasar 438BEstimated53.6%
  4. #27Qwen3.8 Max (0902)51.0%
estimated from related benchmarks
Terminal-Bench 4.0
day 0
#39/830.5%Verified
  1. #1Claude Sonnet 5.563.6%
  2. #39North Mini Code0.5%
  3. #39Ring-2.6-1T0.5%
  4. #39Solar Pro 40.5%
artificialanalysis.ai · 2026-09-24
#49/830.0%Verified
  1. #1Claude Sonnet 5.563.6%
  2. #49Ling 3.0 Tiny0.0%
  3. #49Ling-3.0-flash-Fin0.0%
  4. #49Ling-3.0-flash-VL0.0%
artificialanalysis.ai · 2026-09-24
#32/831.0%BestVerified
  1. #1Claude Sonnet 5.563.6%
  2. #32Kimi K2.7 Code1.0%
  3. #32Quasar 438B1.0%
  4. #32Qwen3.7 Plus1.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBench
third-party
~#8/20~69.2%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #7gpt-oss-20b77.7%
  3. ~#8Ring-2.6-1TEstimated69.2%
  4. #8Mistral Small 464.0%
estimated from related benchmarks
~#8/20~66.3%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #7gpt-oss-20b77.7%
  3. ~#8Ling-3.0-flash-FinEstimated66.3%
  4. #8Mistral Small 464.0%
estimated from related benchmarks
~#8/20~72.9%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #7gpt-oss-20b77.7%
  3. ~#8Quasar 438BEstimated72.9%
  4. #8Mistral Small 464.0%
estimated from related benchmarks
SciCode
third-party
#42/9545.0%Verified
  1. #1Claude Opus 5.566.9%
  2. #40Gemma 4 31B45.5%
  3. #42Ring-2.6-1T45.0%
  4. #43Muse Glimmer44.9%
artificialanalysis.ai · 2026-09-24
#51/9542.4%Verified
  1. #1Claude Opus 5.566.9%
  2. #50K2 Horizon 375B A23B42.9%
  3. #51Ling-3.0-flash-Fin42.4%
  4. #52Claude Haiku 4.542.2%
artificialanalysis.ai · 2026-09-24
#31/9548.1%BestVerified
  1. #1Claude Opus 5.566.9%
  2. #30Hy348.6%
  3. #31Quasar 438B48.1%
  4. #32Solar Open2 250B48.0%
artificialanalysis.ai · 2026-09-24
AA Coding Agent Index
third-party
~last/15below measured range (<41.1)Estimated
  1. #1Claude Opus 5.566.0
  2. #14GPT-6 Luna41.1
  3. ~#15Ring-2.6-1TEstimated<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. ~#15Ling-3.0-flash-FinEstimated<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. ~#15Quasar 438BEstimated<41.1
estimated from related benchmarks
Benchmarks in other categories (3)

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
Ring-2.6-1T
Ling-3.0-flash-Fin
Quasar 438B
IFBench
day 0
#66/12544.6%Verified
  1. #1MiniMax-M382.9%
  2. #65Gemma 4 12B45.2%
  3. #66Ring-2.6-1T44.6%
  4. #67Magistral Small 1.244.4%
artificialanalysis.ai · 2026-09-24
—
—
MMMLU
day 0
~last/5below measured range (<81.3%)Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. #4gpt-oss-120b81.3%
  3. ~#5Ring-2.6-1TEstimated<81.3%
estimated from related benchmarks
—
—
LMArena Text, Non-English (Elo)
third-party
~#41/54~1368Estimated
  1. #1Claude Opus 5.51501
  2. #40Qwen3 Next 80B A3B Instruct1386
  3. ~#41Ring-2.6-1TEstimated1368
  4. #41GLM-4.6VFew votes1361
estimated from related benchmarks
—
—
LMArena Text (Elo)
third-party
~#41/54~1387Estimated
  1. #1Claude Opus 5.51509
  2. #40Qwen3 Next 80B A3B Instruct1399
  3. ~#41Ring-2.6-1TEstimated1387
  4. #41GLM-4.6VFew votes1378
estimated from related benchmarks
—
—
EQ-Bench Creative Writing v3 (Elo)
third-party
~#23/26~1403Estimated
  1. #1GPT-6 Astra2173
  2. #22Mistral Large 31412
  3. ~#23Ring-2.6-1TEstimated1403
  4. #23Gemma 4 31B1368
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
Ring-2.6-1T
Ling-3.0-flash-Fin
Quasar 438B
GPQA Diamond
day 0
#39/17285.7%BestVerified
  1. #1GPT-6 Astra96.1%
  2. #39Qwen3.5 122B A10B85.7%
  3. #39Ring-2.6-1T85.7%
  4. #39Solar Open2 250B85.7%
artificialanalysis.ai · 2026-09-24
~#80/173~74.9%Estimated
  1. #1GPT-6 Astra96.1%
  2. #78Trinity Large Thinking75.2%
  3. ~#80Ling-3.0-flash-FinEstimated74.9%
  4. #80Mistral Medium 3.574.8%
estimated from related benchmarks
#88/17273.2%Verified
  1. #1GPT-6 Astra96.1%
  2. #86HyperNova 60B 260573.3%
  3. #88Quasar 438B73.2%
  4. #89Llama 3.1 Nemotron Ultra 253B v172.8%
artificialanalysis.ai · 2026-09-24
Humanity's Last Exam
day 0
#59/17821.6%Verified
  1. #1Claude Opus 5.561.4%
  2. #58Intern-S2-Preview (35B-A3B)21.9%
  3. #59Ring-2.6-1T21.6%
  4. #60Step 3.7 Flash21.4%
artificialanalysis.ai · 2026-09-24
#54/17822.6%BestVerified
  1. #1Claude Opus 5.561.4%
  2. #53K2 Horizon MoVA 36B A4B23.4%
  3. #54Ling-3.0-flash-Fin22.6%
  4. #55Qwen3.6 35B A3B22.2%
artificialanalysis.ai · 2026-09-24
#67/17818.7%Verified
  1. #1Claude Opus 5.561.4%
  2. #66Gemini 3.5 Flash-Lite18.8%
  3. #67Quasar 438B18.7%
  4. #68K-EXAONE 2.0 080318.6%
artificialanalysis.ai · 2026-09-24
AIME (latest)
day 0
~#6/25~89.7%Estimated
  1. #1Inkling97.1%
  2. #5Xing4.0-29B-A4B90.0%
  3. ~#6Ring-2.6-1TEstimated89.7%
  4. #6gpt-oss-20b89.3%
estimated from related benchmarks
~#4/25~93.6%Estimated
  1. #1Inkling97.1%
  2. #3Nova 2.0 Lite94.3%
  3. ~#4Ling-3.0-flash-FinEstimated93.6%
  4. #4gpt-oss-120b93.4%
estimated from related benchmarks
~#12/25~80.5%Estimated
  1. #1Inkling97.1%
  2. #11Claude Haiku 4.583.7%
  3. ~#12Quasar 438BEstimated80.5%
  4. #12Magistral Small 1.280.3%
estimated from related benchmarks
AA Intelligence Index
third-party
#49/7416.6Verified
  1. #1Claude Opus 5.557.6
  2. #48Claude Haiku 4.516.9
  3. #49Ring-2.6-1T16.6
  4. #50K2 Horizon 3.7B15.6
artificialanalysis.ai · 2026-09-24
#40/7422.6Verified
  1. #1Claude Opus 5.557.6
  2. #39Nemotron 3 Ultra22.9
  3. #40Ling-3.0-flash-Fin22.6
  4. #41Gemini 3.5 Flash-Lite22.2
artificialanalysis.ai · 2026-09-24
#29/7426.7BestVerified
  1. #1Claude Opus 5.557.6
  2. #28MiniMax-M329.2
  3. #29Quasar 438B26.7
  4. #30Apodex 1.126.4
artificialanalysis.ai · 2026-09-24

Agents benchmarks

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

Metric
Ring-2.6-1T
Ling-3.0-flash-Fin
Quasar 438B
τ²-bench (Telecom)
day 0
#10/11592.4%Verified
  1. #1Step 3.7 Flash98.5%
  2. #9Nova 2.0 Pro Preview92.7%
  3. #10Ring-2.6-1T92.4%
  4. #11MiMo-V2.590.6%
artificialanalysis.ai · 2026-09-24
—
~#40/116~67.6%Estimated
  1. #1Step 3.7 Flash98.5%
  2. #39Nemotron 3 Super 120B A12B67.8%
  3. ~#40Quasar 438BEstimated67.6%
  4. #40gpt-oss-120b65.8%
estimated from related benchmarks
OSWorld-Verified
day 0
~#11/12~63.8%Estimated
  1. #1Kimi K384.8%
  2. #10Muse Glimmer65.9%
  3. ~#11Ring-2.6-1TEstimated63.8%
  4. #11Claude Haiku 4.550.7%
estimated from related benchmarks
—
~#10/12~70.2%Estimated
  1. #1Kimi K384.8%
  2. #9Nex-N2.5-Mini71.2%
  3. ~#10Quasar 438BEstimated70.2%
  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. ~#5Ring-2.6-1TEstimated<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. ~#5Quasar 438BEstimated<47.5%
estimated from related benchmarks
BrowseComp
day 0
~#15/18~61.6%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #14Inkling77.1%
  3. ~#15Ring-2.6-1TEstimated61.6%
  4. #15Mistral Medium 3.548.6%
estimated from related benchmarks
—
~#15/18~70.3%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #14Inkling77.1%
  3. ~#15Quasar 438BEstimated70.3%
  4. #15Mistral Medium 3.548.6%
estimated from related benchmarks
GDPval-AA (Elo)
third-party
#52/86734Verified
  1. #1Claude Opus 5.51846
  2. #51Mistral Medium 3.5747
  3. #52Ring-2.6-1T734
  4. #53KAT Coder Pro V2720
artificialanalysis.ai · 2026-09-24
—
#29/861162BestVerified
  1. #1Claude Opus 5.51846
  2. #28K2 Horizon MoVA 36B A4B1181
  3. #29Quasar 438B1162
  4. #30Ling-3.0-flash-VL1150
artificialanalysis.ai · 2026-09-24
AutomationBench-AA
third-party
#68/790.7%Verified
  1. #1Claude Opus 5.569.5%
  2. #68Ministral 3 3B0.7%
  3. #68Ring-2.6-1T0.7%
  4. #70Ministral 3 14B0.6%
artificialanalysis.ai · 2026-09-24
—
#33/7923.9%BestVerified
  1. #1Claude Opus 5.569.5%
  2. #32Kimi K2.7 Code24.5%
  3. #33Quasar 438B23.9%
  4. #34MiniMax-M321.3%
artificialanalysis.ai · 2026-09-24
τ-Bench Banking (AA)
third-party
#40/8817.9%Verified
  1. #1Muse Spark 1.350.5%
  2. #39Inkling Small18.8%
  3. #40Ring-2.6-1T17.9%
  4. #41Gemini 3.5 Flash-Lite17.5%
artificialanalysis.ai · 2026-09-24
—
#23/8828.7%BestVerified
  1. #1Muse Spark 1.350.5%
  2. #22Inkling29.1%
  3. #23Quasar 438B28.7%
  4. #24K2 Horizon 7B27.6%
artificialanalysis.ai · 2026-09-24