Compare / Gemini 2.5 Pro vs Grok 4.20
Gemini 2.5 Pro vs Grok 4.20
Which is cheaper, which is more capable, and which does better at each kind of work, from 10 results on 3 sources that measured both models.
Gemini 2.5 Pro or Grok 4.20? The short answer
- Grok 4.20 is cheaper: $1.56 against $3.44 per million tokens, 2.2 times less.
- Grok 4.20 scores higher on the Artificial Analysis Intelligence Index: 25.7 against 16.1.
- On our business benchmarks, Grok 4.20 ranks higher for agents and tool use and reasoning and knowledge.
At a glance
| Gemini 2.5 Pro | Grok 4.20 | |
|---|---|---|
| Price per million tokens | $1.25 in · $10.00 out | $1.25 in · $2.50 out |
| Blended (3 in : 1 out) | $3.44 | $1.56 |
| Cheapest host, blended | $1.72 (Google AI Studio) | $1.56 (xAI) |
| Intelligence Index | 16.1 | 25.7 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 1,048,576 tokens | 2,000,000 tokens |
| Weights | Closed | Closed |
| Developer based in | the US | the US |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | Gemini 2.5 Pro | Grok 4.20 |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 109 of 161 | 73 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 92 of 195 | 51 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 42 of 187 | not measured |
| Sticking to the factsSummarising without inventing things, and factual answers | 38 of 153 | not measured |
Every shared result
| Benchmark | Metric | Gemini 2.5 Pro | Grok 4.20 |
|---|---|---|---|
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 16.1 | 25.7 |
| Artificial Analysisreported | GPQA Diamond% of questions | 84.4% | 91.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 22.5% | 34.5% |
| Artificial Analysisreported | IFBench% of instructions | 48.7% | 81.2% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 69.0% | 69.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 26.5% | 37.9% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 54.1% | 93.0% |
| tau2-benchreported | Consistency (pass^4)% of tasks | 1.0% | 8.2% |
| tau2-benchreported | Task success (pass^1)% of tasks | 13.7% | 18.0% |
| Vending-Bench 2reported | Money after a yearUS dollars | $573.64 | $4,662.85 |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.
Quick answers
Is Gemini 2.5 Pro better than Grok 4.20?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Grok 4.20 ranks higher for agents and tool use and reasoning and knowledge.
Which is cheaper, Gemini 2.5 Pro or Grok 4.20?
Grok 4.20 costs $1.56 per million tokens (three input to one output), against $3.44 for Gemini 2.5 Pro.
Run Gemini 2.5 Pro and Grok 4.20 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.