Skip to content
Model Pareto

GPT-6.1 Terra vs GPT-5.6 Terra

GPT-6.1 Terra scores higher than GPT-5.6 Terra in both shared categories. GPT-5.6 Terra costs 2.3× as much as GPT-6.1 Terra ($4.50 vs $2.00 per million tokens, blended 3:1 input:output).
GPT-6.1 TerraGPT-5.6 Terra
Focus

Coding: quality vs price

Compared models are ringed; the other 132 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, GPT-6.1 Terra, Kimi K3.1 Pro, Claude Opus 5.5. 41 models are not plotted: Muse Wonder Full, GLM-5.3 Flash NVFP4, DeepSeek V4.1 Flash NVFP4, DeepSeek-V4-Pro-0813-nvfp4-DSpark, GLM-5.3 NVFP4, Atria Dawn Preview, Xing4.0-29B-A4B, Ternary Bonsai 27B, Beam 1.0 501B A23B, Maple-Preview, Qwen3.8 27B NVFP4, Intern-S2-397B, Bonsai 27B, Solar Open2 250B, Muse Spark Open, Laguna S 2.1, Phi-4-reasoning-plus, Flint, Motif 3, Nex-N2-Pro, Nemotron 3.5 Super VL NVFP4, Nemotron 3.5 Super VL, K2 Horizon 375B A23B, K-EXAONE 2.0 0803, A.X-K2, Nemotron 3.5 Bolt 74B-A9B, Intern-S2-Preview (35B-A3B), K2 Horizon MoVA 36B A4B, North Mini Code, G9v3-39A5B, Qwen3.8 Flash-Next NVFP4, K2 Horizon 7B, K2-Horizon-32B, LFM2.5-24B-A2B, NVIDIA Nemotron-Labs Dory1.0 4B, MiniCPM5-2B, Falcon-H1-34B-Instruct, Ling 3.0 Tiny, K2 Horizon 3.7B, K2 Horizon 0.9B, LFM2.5-2.6B.

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

Muse Wonder Full, GLM-5.3 Flash NVFP4, DeepSeek V4.1 Flash NVFP4, DeepSeek-V4-Pro-0813-nvfp4-DSpark, GLM-5.3 NVFP4, Atria Dawn Preview, Xing4.0-29B-A4B, Ternary Bonsai 27B, Beam 1.0 501B A23B, Maple-Preview, Qwen3.8 27B NVFP4, Intern-S2-397B, Bonsai 27B, Solar Open2 250B, Muse Spark Open, Laguna S 2.1, Phi-4-reasoning-plus, Flint, Motif 3, Nex-N2-Pro, Nemotron 3.5 Super VL NVFP4, Nemotron 3.5 Super VL, K2 Horizon 375B A23B, K-EXAONE 2.0 0803, A.X-K2, Nemotron 3.5 Bolt 74B-A9B, Intern-S2-Preview (35B-A3B), K2 Horizon MoVA 36B A4B, North Mini Code, G9v3-39A5B, Qwen3.8 Flash-Next NVFP4, K2 Horizon 7B, K2-Horizon-32B, LFM2.5-24B-A2B, NVIDIA Nemotron-Labs Dory1.0 4B, MiniCPM5-2B, Falcon-H1-34B-Instruct, 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
  • GPT-6.1 Terra
    Quality
    84.0
    Rank
    #10/134
    Price
    $2.00/M tok
    Speed
    91tok/s
    In$1.00▾Out$5.00▾/M tok

    vs GPT-5.6 Terra: +14.6 quality · 0.44× price

  • GPT-5.6 Terra
    Quality
    69.5
    Rank
    #22/134
    Price
    $4.50/M tok
    Speed
    104tok/s
    In$2.00Out$12/M tok

    vs GPT-6.1 Terra: −14.6 quality · 2.3× price

Overview

Metric
GPT-6.1 Terra
GPT-5.6 Terra
Lab
OpenAI
OpenAI
Released
Oct 26, 2026
Jul 9, 2026
Weights
Proprietary
Proprietary
Input price
$/M tok
$1.00Best
$2.00
Output price
$/M tok
$5.00Best
$12
Blended price
$/M tok · 3:1 in:out
$2.00Best
$4.50
Output speed
tok/s
91
104Best
Context
tokens
1.1MBest
1M

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
GPT-6.1 Terra
GPT-5.6 Terra
Coding
84.0±10.2Best
#10/134Lab-reportedbest value
69.5±5.3
#22/134Mixed
Writing & chat
Not ranked
69.0±3.3
#29/160Verified
Vision
Not ranked
76.9±4.8
#13/97Verified
Hard reasoning
90.0±8.3Best
#11/215Verifiedbest value
79.1±3.7
#26/215Verified
Agents
Not ranked
71.4±3.2
#27/186Mixed

Coding benchmarks

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

Metric
GPT-6.1 Terra
GPT-5.6 Terra
SWE-bench Verified
day 0
~#2/20~93.4%Estimated
  1. #1Claude Opus 596.0%
  2. ~#2GPT-6.1 TerraEstimated93.4%
  3. #2Claude Sonnet 585.2%
estimated from related benchmarks
~#2/20~85.4%Estimated
  1. #1Claude Opus 596.0%
  2. ~#2GPT-5.6 TerraEstimated85.4%
  3. #2Claude Sonnet 585.2%
estimated from related benchmarks
SWE-bench Pro (Public)
day 0
~#5/23~77.2%Estimated
  1. #1Claude Opus 5.589.9%
  2. #4Claude Opus 579.2%
  3. ~#5GPT-6.1 TerraEstimated77.2%
  4. #5Intern-S2-397B68.5%
estimated from related benchmarks
#8/2263.4%Lab-reported
  1. #1Claude Opus 5.589.9%
  2. #7Hy4 preview65.7%
  3. #8GPT-5.6 Terra63.4%
  4. #9Claude Sonnet 563.2%
openai.com · 2026-07-09
DeepSWE v1.1
day 0
~#12/43~70.9%Estimated
  1. #1Gemini 4 Argon78.8%
  2. #11Claude Sonnet 5.571.0%
  3. ~#12GPT-6.1 TerraEstimated70.9%
  4. #12GPT-5.6 Terra69.6%
estimated from related benchmarks
#12/4269.6%Lab-reported
  1. #1Gemini 4 Argon78.8%
  2. #11Claude Sonnet 5.571.0%
  3. #12GPT-5.6 Terra69.6%
  4. #13GPT-6 Sol69.0%
openai.com · 2026-07-09
Terminal-Bench 4.0
day 0
#10/9950.3%BestLab-reported
  1. #1Kimi K3.1 Pro67.2%
  2. #8Muse Wonder52.0%
  3. #10GPT-6.1 Terra50.3%
  4. #11Claude Opus 549.0%
bleepingcomputer.com · 2026-10-30
#15/9935.4%Verified
  1. #1Kimi K3.1 Pro67.2%
  2. #14Qwen3.8 Max (0902)38.9%
  3. #15GPT-5.6 Terra35.4%
  4. #16MiMo-V2.6-Pro34.8%
artificialanalysis.ai · 2026-09-24
LiveCodeBench
third-party
~#6/28~88.5%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #5Nemotron 3 Ultra89.0%
  3. ~#6GPT-6.1 TerraEstimated88.5%
  4. #6Beam 1.0 501B A23B88.3%
estimated from related benchmarks
~#10/28~84.6%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #9Nemotron 3.5 Super VL NVFP487.4%
  3. ~#10GPT-5.6 TerraEstimated84.6%
  4. #10Ternary Bonsai 27B82.8%
estimated from related benchmarks
SciCode
third-party
~#8/118~60.5%Estimated
  1. #1Claude Opus 5.566.9%
  2. #7Kimi K3.1 Pro60.8%
  3. ~#8GPT-6.1 TerraEstimated60.5%
  4. #8Muse Wonder60.3%
estimated from related benchmarks
#26/11755.0%Verified
  1. #1Claude Opus 5.566.9%
  2. #26Claude Haiku 5.555.0%
  3. #26GPT-5.6 Terra55.0%
  4. #28GPT-6 Luna54.6%
artificialanalysis.ai · 2026-09-24
AA Coding Agent Index
third-party
~#9/26~53.5Estimated
  1. #1Claude Opus 5.561.7
  2. #8GPT-6.1 Sol54.1
  3. ~#9GPT-6.1 TerraEstimated53.5
  4. #9Gemini 4 Argon53.2
estimated from related benchmarks
~#16/26~46.3Estimated
  1. #1Claude Opus 5.561.7
  2. #15Grok 4.746.6
  3. ~#16GPT-5.6 TerraEstimated46.3
  4. #16DeepSeek V4.1 Flash 101746.3
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
GPT-6.1 Terra
GPT-5.6 Terra
IFBench
day 0
—
#32/13771.2%Verified
  1. #1MiniMax-M382.9%
  2. #31o371.4%
  3. #32GPT-5.6 Terra71.2%
  4. #33NVIDIA Nemotron 3 Nano 30B A3B71.1%
artificialanalysis.ai · 2026-09-24
MMMLU
day 0
—
~#2/5~90.4%Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2GPT-5.6 TerraEstimated90.4%
  3. #2Gemma 4 31B88.4%
estimated from related benchmarks
LMArena Text, Non-English (Elo)
third-party
—
#17/561456Verified
  1. #1Gemini 4 ArgonFew votes1512
  2. #16DeepSeek V4.1 Flash1459
  3. #17GPT-5.6 Terra1456
  4. #18DeepSeek V4 Pro (0813)1448
lmarena.ai · 2026-09-24
LMArena Text (Elo)
third-party
—
#17/561466Verified
  1. #1Gemini 4 Argon1525
  2. #16DeepSeek V4.1 Flash1474
  3. #17GPT-5.6 Terra1466
  4. #18DeepSeek V4 Pro (0813)1463
lmarena.ai · 2026-09-24
EQ-Bench Creative Writing v3 (Elo)
third-party
—
#10/251855Verified
  1. #1GPT-6 Astra2173
  2. #9Muse Spark 1.31906
  3. #10GPT-5.6 Terra1855
  4. #11GPT-5.51844
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
GPT-6.1 Terra
GPT-5.6 Terra
MMMU
day 0
—
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2GPT-5.6 TerraEstimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
MMMU-Pro
day 0
—
#12/8780.7%Verified
  1. #1Claude Opus 5.587.7%
  2. #11Intern-S2-397B81.7%
  3. #12GPT-5.6 Terra80.7%
  4. #13Kimi K380.5%
artificialanalysis.ai · 2026-09-24
CharXiv Reasoning
day 0
—
~#4/12~83.5%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. #3Qwen3.8 Flash-Next84.6%
  3. ~#4GPT-5.6 TerraEstimated83.5%
  4. #4Qwen3.8-Omni-Flash83.5%
estimated from related benchmarks
OmniDocBench v1.5
third-party
—
~#4/8~90.0%Estimated
  1. #1MiniMax-M391.6%
  2. #2Qwen3.8 27B91.1%
  3. ~#4GPT-5.6 TerraEstimated90.0%
  4. #4Gemini 3.1 Pro85.3%
estimated from related benchmarks
GDP.pdf (AA)
third-party
—
#9/4624.0%Verified
  1. #1Muse Wonder Full32.6%
  2. #8GPT-6 Sol24.8%
  3. #9GPT-5.6 Terra24.0%
  4. #10GPT-6 Luna22.8%
artificialanalysis.ai · 2026-09-24
Chartography
third-party
—
#7/2334.0%Verified
  1. #1GPT-6 Astra71.0%
  2. #6Gemini 3.8 Flash40.9%
  3. #7GPT-5.6 Terra34.0%
  4. #8GPT-5.531.0%
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
GPT-6.1 Terra
GPT-5.6 Terra
GPQA Diamond
day 0
~#2/191~95.7%Estimated
  1. #1GPT-6 Astra96.1%
  2. ~#2GPT-6.1 TerraEstimated95.7%
  3. #2Gemini 3.8 Flash95.3%
estimated from related benchmarks
#16/19092.5%Verified
  1. #1GPT-6 Astra96.1%
  2. #15GLM-5.3 NVFP492.7%
  3. #16GPT-5.6 Terra92.5%
  4. #17Hy4 preview92.3%
artificialanalysis.ai · 2026-09-24
Humanity's Last Exam
day 0
~#10/198~52.1%Estimated
  1. #1Claude Opus 5.561.4%
  2. #9Kimi K3.1 Pro52.5%
  3. ~#10GPT-6.1 TerraEstimated52.1%
  4. #10Muse Wonder50.1%
estimated from related benchmarks
#27/19742.9%Verified
  1. #1Claude Opus 5.561.4%
  2. #25Qwen3.8 Max (0902)43.1%
  3. #27GPT-5.6 Terra42.9%
  4. #28GPT-5.3 Codex42.5%
artificialanalysis.ai · 2026-09-24
AIME (latest)
day 0
~#2/33~98.2%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2GPT-6.1 TerraEstimated98.2%
  3. #2Beam 1.0 501B A23B97.7%
estimated from related benchmarks
~#3/33~97.5%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. #2Beam 1.0 501B A23B97.7%
  3. ~#3GPT-5.6 TerraEstimated97.5%
  4. #3Inkling97.1%
estimated from related benchmarks
AA Intelligence Index
third-party
#11/10251.0BestVerified
  1. #1Gemini 4 Carbon59.4
  2. #10GPT-6.1 Sol51.8
  3. #11GPT-6.1 Terra51.0
  4. #12Claude Opus 550.8
artificialanalysis.ai · 2026-10-30
#25/10242.1Verified
  1. #1Gemini 4 Carbon59.4
  2. #24MiniMax-M3.1-Flash42.7
  3. #25GPT-5.6 Terra42.1
  4. #26GLM-5.3 Flash41.8
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
GPT-6.1 Terra
GPT-5.6 Terra
τ²-bench (Telecom)
day 0
—
#24/11986.3%Verified
  1. #1Step 3.7 Flash98.5%
  2. #23Qwen3.5 9B86.8%
  3. #24GPT-5.6 Terra86.3%
  4. #25GPT-5.3 Codex86.0%
artificialanalysis.ai · 2026-09-24
OSWorld-Verified
day 0
—
~#8/15~79.6%Estimated
  1. #1Kimi K384.8%
  2. #7Muse Spark Open80.4%
  3. ~#8GPT-5.6 TerraEstimated79.6%
  4. #8GPT-5.578.7%
estimated from related benchmarks
OSWorld 2.0
day 0
—
#3/450.2%Lab-reported
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. #3GPT-5.6 Terra50.2%
  4. #4GPT-5.547.5%
openai.com · 2026-07-09
BrowseComp
day 0
—
#7/2187.5%Lab-reported
  1. #1Atria Dawn Preview92.5%
  2. #6Step 5 Preview88.7%
  3. #7GPT-5.6 Terra87.5%
  4. #8Gemini 3.1 Pro85.9%
openai.com · 2026-07-09
GDPval-AA (Elo)
third-party
—
#24/901432Verified
  1. #1Claude Opus 5.51866
  2. #23Gemini 3.8 Flash1436
  3. #24GPT-5.6 Terra1432
  4. #25GPT-6 Luna1432
artificialanalysis.ai · 2026-09-24
AutomationBench-AA
third-party
—
#14/8359.6%Verified
  1. #1Muse Wonder Full71.3%
  2. #12Mistral Large 459.9%
  3. #14GPT-5.6 Terra59.6%
  4. #15Claude Fable 5.159.4%
artificialanalysis.ai · 2026-09-24
τ-Bench Banking (AA)
third-party
—
#14/9040.2%Verified
  1. #1Muse Spark 1.350.5%
  2. #13GPT-6 Astra41.4%
  3. #14GPT-5.6 Terra40.2%
  4. #15DeepSeek V4 Pro (0813)39.6%
artificialanalysis.ai · 2026-09-24