Model results
Vending-Bench 2
Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.
Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.
Vending-Bench 2
- Source
- Andon Labs via Epoch AI
- Version
- 2
- Measurement date
- Not reported
- Metric
- USD · Higher is better
- Evaluation scope
- effort unspecified · result date not supplied
Positions are withheld because at least one result lacks explicit independent provenance or a documented evaluation scope. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.
GPT-6 Astra
openai/gpt-6-astra-20260903
15514.7 USD
View modelEvidence aggregatedGPT-6 Sol
openai/gpt-6-sol-20260922
14427.85 USD
View modelEvidence aggregatedGemini 4 Argon
google/gemini-4-argon-20261013
13718.16 USD
View modelEvidence aggregatedClaude Opus 5
anthropic/claude-opus-5
11181.87 USD
View modelEvidence aggregatedClaude Sonnet 5.5
anthropic/claude-sonnet-5-5
11165.28 USD
View modelEvidence aggregatedClaude Opus 4.7
anthropic/claude-opus-4-7
10936.76 USD
View modelEvidence aggregatedGrok 4.7
x-ai/grok-4.7-20260916
10536.83 USD
View modelEvidence aggregatedGPT-5.6 Sol
openai/gpt-5.6-sol-20260709
9619.37 USD
View modelEvidence aggregatedClaude Opus 5.5
anthropic/claude-opus-5-5
9235.25 USD
View modelEvidence aggregatedGrok 4.6
x-ai/grok-4.6-20260810
9047.03 USD
View modelEvidence aggregatedGLM 5.2
z-ai/glm-5.2-20260616
8313.78 USD
View modelEvidence aggregatedGLM 5.3
z-ai/glm-5.3-20260816
8163.61 USD
View modelEvidence aggregatedClaude Opus 4.6
anthropic/claude-opus-4-6
8017.59 USD
View modelEvidence aggregatedGPT-5.5
openai/gpt-5.5-20260423
7523.84 USD
View modelEvidence aggregatedGPT-5.6 Terra
openai/gpt-5.6-terra-20260709
7343.21 USD
View modelEvidence aggregatedClaude Sonnet 4.6
anthropic/claude-sonnet-4-6
7204.14 USD
View modelEvidence aggregatedClaude Sonnet 5
anthropic/claude-sonnet-5
6377.7 USD
View modelEvidence aggregatedGPT-5.4
openai/gpt-5.4-20260305
6144.18 USD
View modelEvidence aggregatedClaude Opus 4.8
anthropic/claude-opus-4-8
5787.43 USD
View modelEvidence aggregatedClaude Fable 5.1
anthropic/claude-fable-5-1
5421.56 USD
View modelEvidence aggregatedGemini 3.5 Flash
google/gemini-3.5-flash-20260519
5396.42 USD
View modelEvidence aggregatedKimi K3
moonshotai/kimi-k3-20260715
5165.04 USD
View modelEvidence aggregatedGemini 3.8 Flash
google/gemini-3.8-flash-20260902
5093.79 USD
View modelEvidence aggregatedClaude Opus 4.5
anthropic/claude-opus-4-5
4967.06 USD
View modelEvidence aggregatedGPT-5.6 Luna
openai/gpt-5.6-luna-20260709
4094.71 USD
View modelEvidence aggregatedGrok 4.5
x-ai/grok-4.5-20260708
3887.43 USD
View modelEvidence aggregatedClaude Sonnet 4.5
anthropic/claude-sonnet-4-5
3838.74 USD
View modelEvidence aggregatedClaude Haiku 5.5
anthropic/claude-haiku-5-5
3602.46 USD
View modelEvidence aggregatedGPT-5.2
openai/gpt-5.2-20251211
3591.33 USD
View modelEvidence aggregatedDeepSeek V4 Pro 0423
deepseek/deepseek-v4-pro-20260423
3284.52 USD
View modelEvidence aggregatedGPT-5.1
openai/gpt-5.1-20251113
1473.43 USD
View modelEvidence aggregatedDeepSeek V3.2 Exp
deepseek/deepseek-v3.2-exp
1034 USD
View modelEvidence aggregatedClaude Haiku 4.5
anthropic/claude-haiku-4-5
458.89 USD
View modelEvidence aggregatedGrok 4.3
x-ai/grok-4.3-20260430
35.26 USD
View modelEvidence aggregatedGPT-5 Mini
openai/gpt-5-mini-2025-08-07
-31.18 USD
View modelEvidence aggregated