Google · Balanced
Gemini 2.0 Pro 0205
Note: This model is now being routed to Gemini 2.5 Pro because Google no longer has the Gemini 2.0 Pro model available and Gemini 2.5 Pro is an across the board improvement.
- Vision
- Audio input
- Input
- Text, Images, Audio
- Output
- Text
- Discovery tier
- Balanced
Pricing
USD per 1M tokens- Input
- $1.99
- Output
- $7.96
- Cache read
- $0.50
Reference prices as published by the model provider. API example
Specifications
- Context window
- 2.1M
- Max output
- 8.2K
Side by side
Gemini 2.0 Pro 0205 compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Gemini 2.0 Pro 0205GoogleThis model | Mistral Code Agent LatestMistralRemove | |
|---|---|---|
| Provider | Mistral | |
| Discovery tier | Balanced | Open weights |
| Added | Feb 5, 2025 | Jun 2, 2026 |
| Limits | ||
| Context window | 2.1MBest | 262.14K |
| Max output | 8.19K | 32.77KBest |
| Average output | — | 316 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $1.99 | $0.40Best |
| Output | $7.96 | $2.00Best |
| Cache read | $0.50 | — |
| Performance | ||
| Request success (24h) | — | 100.0% |
| Benchmark indexes | ||
| Intelligence Index | 8.7Best | 8.6 |
| Coding Index | 25.5 | 31.3Best |
| Math Index | — | 36.7 |
| Capabilities | ||
| Tools | No | Yes |
| Vision | Yes | No |
| Structured output | No | Yes |
| Audio input | Yes | No |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Gemini 2.0 Pro 0205
- Mistral Code Agent Latest
Intelligence Index
- Gemini 2.0 Pro 02058.7
- Mistral Code Agent Latest8.6
Gemini 2.0 Pro 0205: Better than 15% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- Gemini 2.0 Pro 0205: 25.5
- Mistral Code Agent Latest: 31.3Top
Math Index
Composite of the math evaluations
- Gemini 2.0 Pro 0205: —
- Mistral Code Agent Latest: 36.7
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- Gemini 2.0 Pro 0205: —
- Mistral Code Agent Latest: 3.1%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- Gemini 2.0 Pro 0205: —
- Mistral Code Agent Latest: 0.0%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- Gemini 2.0 Pro 0205: —
- Mistral Code Agent Latest: 482 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- Gemini 2.0 Pro 0205: —
- Mistral Code Agent Latest: 544 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- Gemini 2.0 Pro 0205: —
- Mistral Code Agent Latest: 2.4%
AA-LCRv1.1
Reasoning across long documents
- Gemini 2.0 Pro 0205: —
- Mistral Code Agent Latest: 32.3%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Gemini 2.0 Pro 0205: 6.2%Top
- Mistral Code Agent Latest: 3.6%
GPQA Diamond
Graduate-level science questions
- Gemini 2.0 Pro 0205: 62.2%Top
- Mistral Code Agent Latest: 59.4%
MMLU-Pro
Multi-subject knowledge and reasoning
- Gemini 2.0 Pro 0205: 80.5%Top
- Mistral Code Agent Latest: 76.2%
IFBench
Following precise output instructions
- Gemini 2.0 Pro 0205: —
- Mistral Code Agent Latest: 38.1%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- Gemini 2.0 Pro 0205: —
- Mistral Code Agent Latest: 0.0%
SciCode
Scientific computing in Python
- Gemini 2.0 Pro 0205: —
- Mistral Code Agent Latest: 32.8%
LiveCodeBench
Recent competitive programming problems
- Gemini 2.0 Pro 0205: 34.7%
- Mistral Code Agent Latest: 44.8%Top
Math
AIME 2025
Competition mathematics, 2025 problems
- Gemini 2.0 Pro 0205: —
- Mistral Code Agent Latest: 36.7%
AIME
Competition mathematics
- Gemini 2.0 Pro 0205: 36.0%
- Mistral Code Agent Latest: —
MATH-500
Competition math problems
- Gemini 2.0 Pro 0205: 92.3%
- Mistral Code Agent Latest: —
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- Gemini 2.0 Pro 0205: —
- Mistral Code Agent Latest: 18.9%
τ²-Bench Telecom
Tool use in a customer-support simulation
- Gemini 2.0 Pro 0205: —
- Mistral Code Agent Latest: 24.9%
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Gemini 2.0 Pro 0205: —
- Mistral Code Agent Latest: 32.3%
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
- Gemini 2.0 Pro 0205
- Mistral Code Agent Latest
| Leaderboard | Gemini 2.0 Pro 0205 | Mistral Code Agent Latest |
|---|---|---|
| Vision Style Control · Creative Writing | #5 · 1262.4 | Not in top 20 |
Ranks among Noumen catalog models on LMArena leaderboards. Only top-20 placements are listed.LMArena
- Gemini 2.0 Pro 0205
- Mistral Code Agent Latest
| Leaderboard | Gemini 2.0 Pro 0205 | Mistral Code Agent Latest |
|---|---|---|
| SWE-bench Verified | #12 · 57.6% | Not in top 20 |
Ranks among Noumen catalog models on Epoch AI leaderboards. Only top-20 placements are listed.Epoch AI
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Prompt cache hits
- 79.6%
- About $0.80 per 1M input tokens with caching
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-2.0-pro-exp-02-05",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="gemini-2.0-pro-exp-02-05",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Related models
Other Google models, starting with the same family.
