Price Per TokenPrice Per Token
Alpindale
vs
Xai
Xai

Goliath 120B vs Grok 4

A detailed comparison of pricing, benchmarks, and capabilities

Track Your LLM Costs Across Every Provider Broken down by user, feature, and endpoint

107 out of our 483 tracked models have had a price change in March.

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

Goliath 120B wins:

  • Cheaper output tokens

Grok 4 wins:

  • Cheaper input tokens
  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Better at math
  • Supports vision
  • Has reasoning mode
  • Supports tool calls
Price Advantage
Goliath 120B
Benchmark Advantage
Grok 4
Context Window
Grok 4
Speed
Grok 4

Pricing Comparison

Price Comparison

MetricGoliath 120BGrok 4Winner
Input (per 1M tokens)$3.75$3.00 Grok 4
Output (per 1M tokens)$7.50$15.00 Goliath 120B
Cache Read (per 1M)N/A$0.75 Grok 4
Using a 3:1 input/output ratio, Goliath 120B is 22% cheaper overall.

Goliath 120B Providers

No provider data available

Grok 4 Providers

No provider data available

Benchmark Comparison

8
Benchmarks Compared
0
Goliath 120B Wins
0
Grok 4 Wins

Benchmark Scores

BenchmarkGoliath 120BGrok 4Winner
Intelligence Index
Overall intelligence score
-41.5-
Coding Index
Code generation & understanding
-40.5-
Math Index
Mathematical reasoning
-92.7-
MMLU Pro
Academic knowledge
-86.6-
GPQA
Graduate-level science
-87.7-
LiveCodeBench
Competitive programming
-81.9-
Aider
Real-world code editing
-79.6-
AIME
Competition math
-94.3-
Grok 4 significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Other models

Context & Performance

Context Window

Goliath 120B
6,144
tokens
Grok 4
256,000
tokens
Grok 4 has a 98% larger context window.

Speed Performance

MetricGoliath 120BGrok 4Winner
Tokens/secondN/A40.4 tok/s
Time to First TokenN/A11.45s

Capabilities

Feature Comparison

FeatureGoliath 120BGrok 4
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyGoliath 120BGrok 4
LicenseOpen SourceProprietary
AuthorAlpindaleXai
ReleasedNov 2023Jul 2025

Goliath 120B Modalities

Input
text
Output
text

Grok 4 Modalities

Input
imagetext
Output
text

Related Comparisons

Compare Goliath 120B with:

Compare Grok 4 with:

Frequently Asked Questions

Grok 4 has cheaper input pricing at $3.00/M tokens. Goliath 120B has cheaper output pricing at $7.50/M tokens.
Grok 4 scores higher on coding benchmarks with a score of 40.5, compared to Goliath 120B's score of N/A.
Goliath 120B has a 6,144 token context window, while Grok 4 has a 256,000 token context window.
Goliath 120B does not support vision. Grok 4 supports vision.