BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

Cost per task: what one benchmark task costs

What an average task of Artificial Analysis' Intelligence Index cost on each configuration, billed at list price over the whole run. The spread between models is far wider than their per-token prices, because verbose reasoning multiplies the token count.

As of 9 Nov 2026, BenchLeader ranks GPT-6 Luna first on the Cost per task: what one benchmark task costs board at $0.0051, ahead of Mistral Small 4 ($0.040) and Granite 4.2 8B ($0.040).

138 models · data as of 9 Nov 2026

Quality against what it costs to get there

Model size
40506070$0.0050$0.010$0.020$0.050$0.100$0.200$0.500$1.00$2.00$5.00$10.00$20.00What an average Intelligence Index task cost ($, log scale)BenchLeader Index v1.4Claude Fable 5.2Claude Opus 5.5Claude Fable 5.2NEW Claude Fable 5.2Claude Fable 5.2Gemini 4 CarbonGemini 4 CarbonGPT-6 AstraGPT-6.1 SolGPT-6.1 SolClaude Fable 5.1GPT-6 AstraGPT-6 AstraClaude Fable 5.2GPT-6 AstraGemini 4 ArgonClaude Opus 5.5Claude Opus 5.5Claude Fable 5.2Claude Opus 5Claude Opus 5Claude Sonnet 5.5GPT-6.1 TerraGPT-6.1 TerraClaude Fable 5.1GPT-6 AstraGemini 4 CarbonGPT-6.1 SolGPT-6.1 SolClaude Fable 5.1Claude Fable 5.1GPT-6 SolGPT-6.1 SolClaude Sonnet 5.5GPT-6 AstraMuse WonderGemini 3.8 FlashGemini 3.8 FlashMuse Spark 1.3Claude Fable 5.1Claude Opus 5.5Kimi K3.1 ProGPT-5.6 TerraGPT-5.6 TerraGemini 3.8 FlashGPT-6.1 SolGPT-6.1 TerraGPT-6.1 TerraClaude Opus 5.5GLM 5.3Qwen3.8 MaxQwen3.8 MaxDeepSeek V4.1 Flash 1017Claude Fable 5.1GPT-6.1 TerraInkling 2 SmallGrok 4.7Claude Sonnet 5.5Grok 4.6Grok 4.6MiMo-V2.6-ProGrok 4.7Grok 4.7DeepSeek V4 ProGLM 5.3 FlashGLM 5.3 FlashClaude Haiku 5.5Claude Haiku 5.5GPT-6.1 TerraGPT-6 LunaMiniMax M3Muse WonderMuse WonderGPT-5.6 LunaClaude Haiku 5.5Grok 4.7Hy4Hy4MiMo-V2.6-FlashMiMo-V2.6-FlashStep 5 PreviewGLM 5.3 FlashMiniMax M3.1 FlashMiniMax M3.1 FlashKimi K3Kimi K3Muse Spark OpenMuse Spark OpenGemini 3.1 Flash LiteQwen3.8 27BQwen3.8 27BMistral Large 4Mistral Large 4Inkling SmallGPT-6 LunaGPT-6.1 TerraGemini 3.5 Flash LiteGPT-6 LunaDeepSeek V4.1 Flash 1017Claude Sonnet 5.5Claude Sonnet 5.5Claude Sonnet 5.5Agnes 2.5 Pro ThetaLing 3.1 FlashLing 3.1 FlashQwen3.8 27BClaude Haiku 5.5Claude Haiku 5.5InklingInklingGPT-6 LunaGPT-6 LunaMistral Large 4Nemotron 3 Ultra 550B A55BNemotron 3 Ultra 550B A55BQwen3.8 27BGemini 3.1 Flash LiteGemini 3.5 Flash LiteClaude Haiku 5.5GLM 5.3GLM 5.3Inkling SmallInkling SmallMistral Medium 3.5Mistral Medium 3.5Muse GlimmerMuse GlimmerGPT-6 LunaNemotron 3.5 Super VLBeam 1.0Beam 1.0Qwen3.8 27BClaude Haiku 4.5DeepSeek V4.1 Flash 1017DeepSeek V4 ProDeepSeek V4 ProMistral Medium 3.5Nemotron 3.5 LightningNemotron 3.5 LightningGranite 4.2 8BGranite 4.2 8BMistral Small 4Mistral Small 4GPT-6 Luna
Purple: the frontier, the models no other model shown beats on both axes. Dashed ring: new in the last seven days.

The purple line is the efficiency frontier: at each price, the best index anyone reaches. A model above and left of the rest gives you more quality per dollar of real work. Size bands, task costs and token counts come from Artificial Analysis, which is the only source that publishes what a fixed batch of work actually cost and how much a model wrote for it.

Top 15 by $ per task
  1. 1GPT-6 Luna (low)$0.0051
  2. 2Mistral Small 4 (thinking)$0.040
  3. 3Granite 4.2 8B$0.040
  4. 4Claude Haiku 5.5 (low)$0.044
  5. 5GPT-6.1 Terra (low)$0.071
  6. 6Muse Ember (xhigh)$0.116
  7. 7MiMo-V2.6-Flash$0.129
  8. 8GPT-6.1 Sol (low)$0.161
  9. 9Muse Glimmer (high)$0.170
  10. 10Gemini 3.1 Flash Lite$0.194
  11. 11Inkling Small$0.203
  12. 12MiMo-V2.6-Pro$0.257
  13. 13Beam 1.0$0.284
  14. 14Nemotron 3.5 Lightning$0.290
  15. 15GPT-5.6 Luna (max)$0.331
53 of 53
#
1Claude Opus 5max$11.8265.1$10.00
2Qwen3.8 Maxmax$10.0258.9$3.00
3Gemini 4 Argonhigh$9.9565.7$4.00
4Gemini 4 Carbonmedium$6.5964.1$8.00
5Gemini 3.8 Flashmedium$6.2660.3$1.50
6Grok 4.6xhigh$4.6857.6$3.00
7Muse Wonderhigh$4.5656.3$8.00
8Claude Fable 5.1low$4.4758.7$20.00
9GPT-5.6 Terramax$3.7360.5$4.50
10Kimi K3.1 Pro$3.6861.2$4.00
11Ling 3.1 Flash$3.1950.8$0.450
12NewClaude Fable 5.2low$3.1065.3$16.00
13Grok 4.7low$2.9255.5$3.00
14GPT-6 Solmax$2.4762.9$4.00
15Muse Spark 1.3max$2.3961.7$2.00
16Kimi K3low$2.3753.7$6.00
17Step 5 Preview$2.3554.6$1.43
18Nemotron 3 Ultra 550B A55Bthinking$2.2349.2$1.13
19Muse Spark Openxhigh$2.0253.6$2.00
20Qwen3.8 27Blow$1.9149.0$1.13
21GLM 5.3low$1.5747.4$2.15
22GPT-6 Astralow$1.4262.2$20.00
23Mistral Large 4medium$1.41–$1.05
24Inklingxhigh$1.3550.1$1.76
25MiniMax M3$1.2956.3$0.525
26NewInkling 2 Small$1.1858.3$0.475
27Mistral Medium 3.5$1.0446.6$3.00
28Hy4$1.0355.3$1.25
29DeepSeek V4 Prono reasoning$0.97742.3$1.98
30Claude Opus 5.5low$0.97659.0$8.00
31Gemini 3.5 Flash Lite$0.69351.5$0.850
32GLM 5.3 Flash$0.58356.8$0.238
33NewAgnes 2.5 Pro Theta$0.57550.8$0.150
34Claude Haiku 4.5thinking$0.53245.3$2.00
35Nemotron 3.5 Super VL$0.52045.8$0.260
36Claude Sonnet 5.5low$0.51150.8$4.00
37MiniMax M3.1 Flash$0.49153.9$0.262
38DeepSeek V4.1 Flash 1017no reasoning$0.42545.0$0.525
39GPT-5.6 Lunamax$0.33156.2$0.450
40Nemotron 3.5 Lightning$0.29041.5$0.095
41Beam 1.0$0.28445.6$0.600
42MiMo-V2.6-Pro$0.25757.1$0.548
43Inkling Small$0.20352.1$0.525
44Gemini 3.1 Flash Lite$0.19452.4$0.563
45Muse Glimmerhigh$0.17046.6$0.525
46GPT-6.1 Sollow$0.16160.2$4.00
47MiMo-V2.6-Flash$0.12954.9$0.175
48NewMuse Emberxhigh$0.116–$0.200
49GPT-6.1 Terralow$0.07156.7$2.00
50Claude Haiku 5.5low$0.04447.8$0.200
51Granite 4.2 8B$0.04041.1$0.108
52Mistral Small 4thinking$0.04040.5$0.262
53GPT-6 Lunalow$0.005145.8$0.200

Cite as: BenchLeader, “Cost per task: what one benchmark task costs”, data as of 9 Nov 2026, https://www.benchleader.com/leaderboards/cost-per-run.