Skip to content

AI model leaderboard

222 ranked models by overall score and by category. Scores carry 90% intervals: when two intervals overlap, the order between those models is not certain.

Columns:
222 of 891 models
AI model leaderboard: Overall
FeaturesIntelligencePriceSpeed
Select to compareTypeMode
1Claude Opus 5.5VerifiedAnthropicProprietaryReasoning1M—Sep 22, 202686.7
82–92
87.597.386.165.31516$4.00$20.00$8.00✓—
2GPT-6.1 SolVerifiedOpenAIProprietaryReasoning1.05M—Sep 29, 202684.2
80–88
74.197.390.5—1448$2.00$10.00$4.00✓—
3GPT-6 AstraVerifiedOpenAIProprietaryReasoning1.05M—Sep 3, 202684.0
80–89
76.497.393.386.51443$10.00$50.00$20.00✓—
4Claude Fable 5.1VerifiedAnthropicProprietaryReasoning1M—Sep 1, 202683.2
80–87
91.296.885.259.81512$10.00$50.00$20.00✓—
5Gemini 4 ArgonVerifiedGoogleProprietaryReasoning1M—Sep 30, 202682.9
80–86
74.092.886.979.61532$2.00$10.00$4.00✓—
6Claude Sonnet 5.5VerifiedAnthropicProprietaryReasoning1M—Sep 28, 202682.2
76–88
87.595.281.878.81470$2.00$10.00$4.00✓—
7Claude Fable 5VerifiedAnthropicProprietaryReasoning1M—Jun 9, 202681.3
78–84
90.396.084.382.91491$10.00$50.00$20.00✓—
8Claude Opus 5VerifiedAnthropicProprietaryReasoning1M—Jul 24, 202680.1
77–83
90.491.681.085.21508$5.00$25.00$10.00✓—
9GPT-6 SolVerifiedOpenAIProprietaryReasoning1.05M—Sep 22, 202678.6
75–82
77.597.373.173.71398$2.00$10.00$4.00✓—
10GPT-5.6 SolVerifiedOpenAIProprietaryReasoning1.05M—Jul 9, 202675.3
73–78
64.795.876.483.71457$4.00$20.00$8.00✓—
11Muse Wonder FullProvisionalMetaProprietaryReasoning1M—Oct 12, 202674.8
60–89
69.0—82.5——————
12MiMo-V2.6-ProProvisionalXiaomiOpen weightsReasoning1M1.02TSep 22, 202673.7
64–83
63.3—82.577.81491$0.43$0.87$0.54—
13GPT-5.5 ProProvisionalOpenAIProprietaryReasoning1M—Apr 23, 202673.5
59–88
—94.078.980.4—$30.00$180.00$67.50✓—
14Muse WonderProvisionalMetaProprietaryReasoning1M—Oct 12, 202671.5
57–86
——80.4—1501$4.00$20.00$8.00—
15GPT-5.6 TerraVerifiedOpenAIProprietaryReasoning1.05M—Jul 9, 202670.2
67–74
64.390.169.176.01447$2.00$12.00$4.50✓—
16Claude Opus 4.8VerifiedAnthropicProprietaryReasoning1M—May 28, 202670.0
66–74
75.184.462.874.11461$5.00$25.00$10.00✓—
17Kimi K3VerifiedMoonshot AIOtherReasoning1.05M—Jul 16, 202670.0
66–74
74.6—69.881.91475$3.00$15.00$6.00—
18Qwen3.8 MaxVerifiedAlibabaOpen weightsReasoning1M—Aug 3, 202669.7
66–74
70.678.987.082.91483————
19Step 5 PreviewProvisionalStepFunOpen weightsReasoning1M604BSep 20, 202669.6
60–79
77.6—82.578.51441$1.00$2.70$1.43—
20GPT-5.5VerifiedOpenAIProprietaryReasoning1M—Apr 23, 202669.2
63–75
55.591.270.381.71471$5.00$30.00$11.25✓—
21Gemini 3.8 FlashVerifiedGoogleProprietaryReasoning1M—Sep 2, 202669.2
64–75
77.569.774.372.61499$0.75$3.75$1.50✓—
22GPT-5.4 ProProvisionalOpenAIProprietaryReasoning1.05M—Mar 5, 202668.7
54–83
—86.578.179.3—$30.00$180.00$67.50—
23Claude Opus 4.7 (Adaptive)ProvisionalAnthropicProprietaryReasoning1M—Apr 16, 202668.7
54–83
65.6—57.471.8—$5.00$25.00$10.00—
24Ling 3.1 FlashProvisionalInclusionAIOpen weightsReasoning262K572BSep 29, 202668.1
54–82
69.1—82.082.3—$0.075$0.23$0.11—
25GLM-5.3VerifiedZ.AIOpen weightsReasoning1M753BAug 14, 202668.0
63–72
58.671.579.874.51472$0.079$1.40$0.41—
26Claude Haiku 5.5ProvisionalAnthropicProprietaryReasoning1M—Oct 7, 202667.2
53–82
64.879.160.1——$0.10$0.50$0.20✓—
27MiniMax M3.1 FlashProvisionalMiniMaxProprietaryReasoning1M—Oct 19, 202667.1
53–81
——79.873.7—$0.15$0.60$0.26—
28Grok 4.6VerifiedxAIProprietaryReasoning500K—Aug 12, 202667.1
64–70
77.370.161.477.61428$2.00$6.00$3.00✓—
29Gemini 3.7 FlashVerifiedGoogleProprietaryReasoning1M—Aug 13, 202666.9
61–73
78.674.881.664.71487$0.75$3.75$1.50—
30GPT-5.4VerifiedOpenAIProprietaryReasoning1.05M—Mar 5, 202666.7
62–71
47.182.064.280.31469$2.50$15.00$5.63✓—
31GPT-5.2 ProProvisionalOpenAIProprietaryReasoning400K—Dec 11, 202566.7
57–76
—————$21.00$168.00$57.75—
32GPT-6 LunaVerifiedOpenAIProprietaryReasoning1.05M—Sep 22, 202666.6
62–71
66.383.759.273.31392$0.10$0.50$0.20✓—
33Muse Spark 1.1VerifiedMetaProprietaryReasoning1M—Jul 9, 202666.1
58–75
60.2—78.466.91478$1.25$4.25$2.00—
34Muse Spark 1.2VerifiedMetaProprietaryReasoning1M—Aug 5, 202665.9
60–72
62.9—79.375.61484$1.25$4.25$2.00—
35DeepSeek V4.1 Flash 1017VerifiedDeepSeekOpen weightsReasoning1M763BOct 17, 202665.7
61–71
62.970.182.5—1463$0.15$0.60$0.26✓—
36Claude Opus 4.7ProvisionalAnthropicProprietaryNon-reasoning1M—Apr 16, 202665.5
56–75
69.072.931.437.61490$5.00$25.00$10.00✓—
37Claude Sonnet 5VerifiedAnthropicProprietaryReasoning1M—Jun 30, 202664.9
60–70
62.869.481.377.51442$2.00$10.00$4.00✓—
38Gemini 3.1 ProProvisionalGoogleProprietaryReasoning1M—Feb 19, 202664.7
55–74
78.165.058.269.0—$2.00$12.00$4.50✓—
39MiMo-V2.6-FlashProvisionalXiaomiOpen weightsReasoning1M311BSep 22, 202664.6
55–74
64.1—76.075.71455$0.14$0.28$0.17—
40GPT-5.6 LunaVerifiedOpenAIProprietaryReasoning1.05M—Jul 9, 202664.4
59–69
56.484.058.270.21431$0.20$1.20$0.45✓—
41dots3-note PreviewProvisionalDots StudioOpen weightsReasoning512K—Aug 14, 202664.1
50–78
57.2—76.671.1—————
42Grok 4.5VerifiedxAIProprietaryReasoning500K—Jul 8, 202663.3
58–69
67.762.954.174.31448$2.00$6.00$3.00✓—
43DeepSeek V4 Pro 0813ProvisionalDeepSeekOpen weightsReasoning1M1.65TAug 13, 202663.2
49–78
59.487.460.773.5—$0.66$1.98$0.99✓—
44Qwen3.8-Flash-NextProvisionalAlibabaOpen weightsReasoning262K180BAug 26, 202662.9
49–77
58.6—79.840.0—————
45Gemini 3.6 FlashVerifiedGoogleProprietaryReasoning1M—Jul 21, 202662.8
55–70
60.663.567.679.51479$0.75$3.75$1.50✓—
46Muse Spark OpenProvisionalMetaOpen weightsReasoning1M822BOct 15, 202662.8
48–77
——78.8——$1.25$4.25$2.00—
47Qwen3.7 MaxVerifiedAlibabaProprietaryReasoning1M—May 16, 202662.6
53–72
65.579.081.473.11475$1.48$4.42$2.21—
48Claude Opus 4.6VerifiedAnthropicProprietaryNon-reasoning1M—Feb 1, 202662.3
50–75
55.069.151.269.81502$5.00$25.00$10.00✓—
49Ornith-1.5-397BProvisionalOrnith AIOpen weightsReasoning262K—Aug 18, 202662.3
48–77
66.7——75.6—————
50Gemini 3.5 FlashVerifiedGoogleProprietaryReasoning1M—May 19, 202661.9
54–70
51.767.170.971.81482$1.50$9.00$3.38—

Speed, latency and end-to-end columns show only our own measurements; a dash means not measured yet.

Page 1 of 5