Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

GDPVal leaderboard — the family board.

7 TRACKED VARIANTS · 2 FIRST-CLASS BOARDS

One family, 7 tracked prints: GDPval-AA v2 is cited standalone and keeps live board of its own. Scoring configs and splits of the base board render as sections of this page, each under its own honest label.

● LIVE DATA321 MODELS ON THIS BOARDLEADER SEED 2.1 PRO PREVIEW AT 87.9

First-class boards in this familyCITED STANDALONE · EACH KEEPS ITS OWN LIVE BOARD

#BoardModels scored
01GDPValTHIS PAGE321

The board — GDPValTOP 100 OF 321 MEASURED · BEST SCORE PER MODEL, DEFAULT VARIANT

#ModelVendorScoreVLast seen
01Seed 2.1 Pro PreviewByteDance87.92026-09-28
02GPT-5.5OpenAI84.92026-09-28
03Claude Opus 4.7Anthropic82.72026-10-04
04Seed2.1ByteDance82.72026-09-28
05Claude Opus 5.5Anthropic68.32026-10-04
06Gemini 3.1 ProGoogle67.32026-09-28
08Claude Fable 5.1Anthropic62.82026-10-04
09Claude Opus 5Anthropic61.22026-10-04
10Grok 4.7SpaceXAI60.62026-10-02
11Kimi K3Moonshot59.42026-07-31
12MiMo V2.6 ProXiaomi59.22026-09-22
13Muse Spark 1.3Meta59.22026-09-03
14Qwen3.8 Max PreviewAlibaba58.62026-09-16
15Gemini 3.5 FlashGoogle57.82026-09-10
16GLM-5.3Z.ai57.52026-09-25
17GLM 5.3 FlashZ.ai57.32026-08-27
18Grok 4.6SpaceXAI57.32026-08-22
19Qwen3.8 Flash NextAlibaba56.62026-08-28
20Gemini 4 ArgonGoogle56.32026-10-01
21Ling-3.1-flashInclusionAI56.12026-10-04
22Haiku 5.5Anthropic56.02026-10-08
23Claude Opus 4.6Anthropic55.92026-06-01
24Claude Fable 5Anthropic55.62026-10-04
25Qwen3.8 2.4T A95BAlibaba55.62026-08-14
26GPT-5.6 SolOpenAI55.62026-07-10
27MiMo V2.6 Flash RLXiaomi55.52026-09-28
28DeepSeek-V4.1-FlashDeepSeek552026-10-01
29Claude Sonnet 4.6Anthropic54.82026-10-04
30GLM-5.1Z.ai54.72026-06-06
31DeepSeek-V4-ProDeepSeek54.62026-10-01
33Step 5 PreviewStepFun54.22026-09-19
34GPT-6.1 SolOpenAI53.82026-09-30
35DeepSeek-V4-FlashDeepSeek52.92026-10-01
36Agnes 3.0 FlashSapiens AI52.52026-09-12
37GPT-6 AstraOpenAI52.12026-09-04
38Kimi K2.6Moonshot50.42026-06-06
39GPT-6 SolOpenAI50.42026-09-23
40Qwen3.6 Max PreviewAlibaba50.22026-05-02
41GPT-5.4OpenAI50.12026-05-02
42GLM-5-TurboZ.ai49.62026-05-02
43GPT-5.3 CodexOpenAI49.02026-05-02
44Muse Spark 1.2Meta48.92026-08-06
45GPT-5.2OpenAI48.32026-05-02
46Claude Sonnet 5Anthropic48.32026-10-04
47GPT-5.6 LunaOpenAI48.22026-07-10
48Nemotron 3 Ultra 550B A55BNVIDIA47.92026-09-01
49Claude Opus 4.8Anthropic47.82026-10-04
50GPT-5.6 TerraOpenAI47.72026-07-10
51MiniMax M2.7MiniMax47.62026-06-06
52Claude Opus 4.5Anthropic47.32026-05-06
53Gemini 3.8 FlashGoogle46.82026-09-03
54GPT-6 LunaOpenAI46.62026-09-23
55Mistral Large 4Mistral46.22026-10-07
56Qwen3.8 27BAlibaba46.22026-08-25
57Step 3.7 FlashStepFun45.82026-09-09
58MiMo V2 ProXiaomi45.22026-05-02
59Gemini 3.7 FlashGoogle44.62026-08-14
60GLM-5Z.ai44.62026-05-02
61Grok4.5SpaceXAI44.52026-07-09
62GLM-5.2Z.ai43.72026-07-11
63K2 Horizon 375B A23BMBZUAI43.32026-09-04
64MiMo V2 OmniXiaomi42.42026-05-02
65GLM 5V TurboZ.ai41.42026-06-01
66JT-4.1 Flash 236B A21BChina Mobile41.42026-09-30
67Gemini 3 Deep ThinkGoogle41.22026-05-02
68Claude 5.5Anthropic41.22026-10-04
69GPT-5.4 miniOpenAI40.82026-06-01
70Grok 4.3SpaceXAI40.62026-05-23
71Agnes 2.5 Pro BetaSapiens AI40.62026-08-27
72Claude Sonnet 4.5Anthropic40.42026-06-01
73MiMo V2.5 ProXiaomi39.92026-07-07
74GPT-5.2 CodexOpenAI39.42026-05-02
75Gemini 3.6 FlashGoogle39.32026-09-10
76Kimi K2.5Moonshot38.32026-06-01
77MiniMax M3MiniMax37.12026-06-04
78Hy3-previewTencent36.52026-05-02
79Qwen3.5 397B A17BAlibaba35.82026-06-06
80GPT-5 CodexOpenAI35.82026-05-02
81Muse Spark 1.1Meta35.72026-07-11
82Gemini 3 Flash PreviewGoogle35.22026-05-02
83GPT-5.4 nanoOpenAI34.92026-06-01
84Apodex 1.1Apodex34.82026-08-31
85K2 Horizon 36B-A4BMBZUAI34.72026-09-15
86GPT-5.1 CodexOpenAI34.62026-05-02
87Qwen3.5 Omni PlusAlibaba34.22026-05-02
88Gemini 3 ProGoogle34.22026-05-02
90MiniMax M2.5MiniMax33.92026-05-02
91GLM-4.7Z.ai33.72026-06-01
92Ling-3.0-flash-VLInclusionAI33.22026-09-11
93Qwen3.5 27BAlibaba33.02026-05-02
94GPT-5OpenAI32.52026-07-03
95GPT-5.5 InstantOpenAI32.22026-07-01
96Claude Haiku 4.5Anthropic31.82026-07-20
97Qwen3.7 MaxAlibaba31.62026-05-20
98Inkling-SmallThinking Machines31.22026-07-31
99Claude Sonnet 4Anthropic31.22026-06-01
100Motif-3Motif Technologies31.12026-08-13
◆ IV — INDEPENDENTLY VERIFIED · ◆ AA — AGGREGATOR · ◆ VA — VENDOR · ◇ SA — SOURCE-ATTRIBUTED

Variants of this boardSCORING CONFIGS & SPLITS — NOT CITED STANDALONE, SO THEY LIVE HERE

GDPval-AA (Elo)

VARIANT19 models · best score per model
#ModelVendorScoreVLast seen
01Claude Fable 5Anthropic19322026-06-12
02Claude Opus 4.8Anthropic18902026-07-08
03Claude Opus 5Anthropic18272026-09-22
04Claude Opus 5.5Anthropic18202026-09-22
05GPT-5.5OpenAI17692026-06-12
06Claude Opus 4.7Anthropic17532026-07-06
07Claude Fable 5.1Anthropic17352026-09-22
08Claude Sonnet 4.6Anthropic16762026-07-06
09GPT-5.4OpenAI16742026-07-04
10Gemini 3.5 FlashGoogle16562026-08-24
11Claude Opus 4.6Anthropic16192026-07-04
12DeepSeek-V4-ProDeepSeek15542026-06-27
13GLM-5.1Z.ai15352026-06-06
14Kimi K2.6Moonshot14822026-06-27
15GPT-5.2OpenAI14622026-05-01

GDPval-AA v2 Elo

VARIANT19 models · best score per model
#ModelVendorScoreVLast seen
01Claude Fable 5.1Anthropic18352026-09-01
02Claude Opus 5Anthropic18242026-09-11
03Claude Fable 5Anthropic17472026-09-01
04GPT-5.6 SolOpenAI17362026-09-11
05Kimi K3Moonshot16862026-07-27
06Muse Spark 1.2Meta16282026-08-14
07Claude Opus 4.8Anthropic15932026-07-27
08GPT-5.6 LunaOpenAI15842026-07-22
09Claude Sonnet 5Anthropic15842026-07-22
10Gemini 3.8 FlashGoogle15452026-09-09
11Grok4.5SpaceXAI15352026-07-22
12GPT-5.6 TerraOpenAI15282026-08-14
13GLM-5.2Z.ai15102026-07-27
14GPT-5.5OpenAI14912026-07-27
15Gemini 3.7 FlashGoogle14822026-08-14

Other tracked prints

THIN BOARDSunder 5 published models each — listed, never hidden
PrintLeaderScoreModels
GDPval-MM win rateMiniMax M2.5591

Also tracked, no published surface rows yet: GDPval-AA · gdpval_elo

THE FAMILY BOARD · EVERY PRINT LABELED · EVERY SCORE SOURCE-ATTRIBUTED ON ITS OWN LIVE BOARDAll leaderboardsThe frontier boardModels by vendor