Gemma 4 31B IT TEE
Gemma 4 31B Instruct is a 30.7B dense model with a long context window, multilingual performance, function calling, and configurable reasoning. Running inside a TEE (Trusted Execution Environment), with provider attestation support.
- Reasoning
- Tool Calling
Added May 26, 2026
Model weightsPricing
Auto routing · per 1M tokens- Input
- $0.15
- Output
- $0.46
- Cache read
- $0.075
Specifications
- Context window
- 262.1K
- Max output
- 262.1K
- Parameters
- 31B
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1451.8
Overall Rank
#79 / 421
Votes
6,130
Confidence Interval
1444.4 - 1459.3
Category Scores
Coding
#77 / 416
1,411 votes
1502.1
Math
#59 / 404
430 votes
1467.1
Longer Query
#65 / 399
1,802 votes
1468.8
Creative Writing
#89 / 419
975 votes
1418.3
Instruction Following
#64 / 421
1,801 votes
1453.1
Hard Prompts
#77 / 421
3,565 votes
1475.2
Additional Categories19
Expert
#48 / 371
501 votes
1498.0
Russian
#52 / 385
824 votes
1467.9
Industry Mathematical
#61 / 402
344 votes
1471.2
Hard Prompts English
#68 / 419
1,323 votes
1485.5
Industry Software And It Services
#71 / 421
2,214 votes
1491.8
Industry Life And Physical And Social Science
#74 / 419
930 votes
1473.4
Multi Turn
#75 / 419
1,121 votes
1465.1
Industry Medicine And Healthcare
#77 / 391
421 votes
1470.9
Spanish
#77 / 304
253 votes
1449.9
Industry Writing And Literature And Language
#78 / 420
1,428 votes
1434.6
English
#79 / 421
2,321 votes
1462.1
Exclude Ties
#79 / 421
4,219 votes
1454.9
Industry Business And Management And Financial Operations
#82 / 414
1,176 votes
1449.1
Non English
#82 / 421
3,809 votes
1437.8
Industry Entertainment And Sports And Media
#88 / 419
1,090 votes
1416.0
Industry Legal And Government
#93 / 393
451 votes
1454.6
Chinese
#94 / 395
521 votes
1478.6
Polish
#98 / 243
203 votes
1435.9
French
#101 / 301
267 votes
1456.8
Published 2026-11-11 · Matched as Gemma 4 31B · CC BY 4.0
LMArena DatasetLeaderboard results
These leaderboards tested Gemma 4 31B, another version of this model.
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Epoch AI Benchmarking Hub Epoch AI data, CC BY 4.0 · Updated Nov 17, 2026 | ||
Epoch Capabilities Index | 144.3 | #84 of 115 |
GPQA Diamond | 75.8% | #87 of 119 |
SimpleQA Verified | 10.4% | #80 of 82 |
OTIS Mock AIME 2024–2025 | 73.3% | #85 of 121 |
EQ-Bench 4 | 1110 | #25 of 31 |
Creative Writing v3 | 1369 | #69 of 96 |
Longform Writing | 56.5 | #62 of 97 |
EQ-Bench 3 | 1464 | #22 of 49 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 23.1 | #121 of 149 |
UGI Willingness | 2.5 | #94 of 149 |
UGI Writing | 43.1 | #72 of 149 |
Filtered and ranked to models on NanoGPT.
Providers
Provider information for this model’s automatic routing. These routes cannot be selected individually.
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
Recommended | $0.15 | $0.46 | $0.075 | N/A | N/A |
| $0.15 | $0.46 | $0.075 | N/A | N/A |